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 2	99.95 1	98.13 2	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 2	97.58 2	99.94 1	99.85 2

LTVRE_ROB	93.87 1	97.93 3	98.16 2	97.26 30	98.81 31	93.86 35	99.07 2	98.98 9	97.01 18	98.92 6	98.78 19	95.22 46	98.61 183	96.85 10	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 4	97.60 9	97.93 3	99.02 13	95.95 9	98.61 3	98.81 11	97.41 14	97.28 65	98.46 36	94.62 70	98.84 140	94.64 49	99.53 40	98.99 64

DVP-MVS++		95.93 62	96.34 44	94.70 122	96.54 199	86.66 164	98.45 4	98.22 50	93.26 85	97.54 49	97.36 110	93.12 105	99.38 61	93.88 66	98.68 174	98.04 181

FOURS1					99.21 3	94.68 16	98.45 4	98.81 11	97.73 10	98.27 24

UA-Net		97.35 5	97.24 16	97.69 6	98.22 79	93.87 34	98.42 6	98.19 53	96.95 19	95.46 166	99.23 9	93.45 92	99.57 15	95.34 41	99.89 2	99.63 12

OurMVSNet-221017-0		96.80 20	96.75 25	96.96 39	99.03 12	91.85 61	97.98 7	98.01 88	94.15 65	98.93 5	99.07 10	88.07 209	99.57 15	95.86 26	99.69 17	99.46 22

UniMVSNet_ETH3D		97.13 11	97.72 4	95.35 89	99.51 2	87.38 141	97.70 8	97.54 135	98.16 6	98.94 4	99.33 6	97.84 4	99.08 105	90.73 169	99.73 14	99.59 15

tt0805		95.42 86	95.93 69	93.86 165	98.75 35	88.47 123	97.68 9	94.29 295	96.48 27	95.38 169	93.63 316	94.89 63	97.94 261	95.38 39	96.92 301	95.17 344

HPM-MVS		96.81 19	96.62 30	97.36 27	98.89 22	93.53 42	97.51 10	98.44 24	92.35 100	95.95 138	96.41 189	96.71 11	99.42 38	93.99 65	99.36 65	99.13 48
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPP-MVSNet		93.91 158	93.68 168	94.59 132	98.08 87	85.55 196	97.44 11	94.03 300	94.22 64	94.94 197	96.19 210	82.07 287	99.57 15	87.28 258	98.89 137	98.65 117

mvs5depth		95.28 94	95.82 78	93.66 174	96.42 210	83.08 237	97.35 12	99.28 3	96.44 29	96.20 128	99.65 2	84.10 265	98.01 253	94.06 62	98.93 133	99.87 1

LS3D		96.11 55	95.83 76	96.95 40	94.75 308	94.20 23	97.34 13	97.98 91	97.31 15	95.32 174	96.77 163	93.08 107	99.20 90	91.79 141	98.16 231	97.44 245

HPM-MVS_fast		97.01 12	96.89 22	97.39 25	99.12 8	93.92 32	97.16 14	98.17 59	93.11 87	96.48 107	97.36 110	96.92 6	99.34 68	94.31 57	99.38 62	98.92 81

MVSFormer		92.18 218	92.23 211	92.04 247	94.74 309	80.06 285	97.15 15	97.37 148	88.98 195	88.83 356	92.79 338	77.02 335	99.60 10	96.41 17	96.75 308	96.46 293

test_djsdf		96.62 31	96.49 34	97.01 36	98.55 48	91.77 63	97.15 15	97.37 148	88.98 195	98.26 27	98.86 15	93.35 97	99.60 10	96.41 17	99.45 49	99.66 9

IS-MVSNet		94.49 129	94.35 145	94.92 110	98.25 77	86.46 169	97.13 17	94.31 294	96.24 35	96.28 122	96.36 197	82.88 275	99.35 65	88.19 238	99.52 42	98.96 73

Anonymous20231211		96.60 33	97.13 20	95.00 106	97.46 138	86.35 174	97.11 18	98.24 46	97.58 12	98.72 12	98.97 12	93.15 104	99.15 94	93.18 99	99.74 13	99.50 19

anonymousdsp		96.74 25	96.42 37	97.68 8	98.00 98	94.03 29	96.97 19	97.61 127	87.68 230	98.45 22	98.77 20	94.20 81	99.50 24	96.70 12	99.40 60	99.53 17

ACMMP		96.61 32	96.34 44	97.43 22	98.61 41	93.88 33	96.95 20	98.18 55	92.26 103	96.33 115	96.84 160	95.10 52	99.40 51	93.47 84	99.33 72	99.02 61
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 7	97.64 7	96.33 55	99.01 15	90.77 79	96.90 21	98.60 16	96.30 34	97.74 41	98.00 55	96.87 8	99.39 54	95.95 23	99.42 54	98.84 91

APDe-MVS		96.46 39	96.64 29	95.93 66	97.68 124	89.38 100	96.90 21	98.41 27	92.52 95	97.43 56	97.92 66	95.11 51	99.50 24	94.45 53	99.30 79	98.92 81
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
tt0320		96.97 14	97.64 7	94.96 109	98.89 22	86.86 157	96.85 23	98.45 23	98.29 4	98.88 7	99.45 3	96.48 13	98.54 193	91.73 144	99.72 15	99.47 21

EGC-MVSNET		80.97 392	75.73 410	96.67 46	98.85 27	94.55 19	96.83 24	96.60 212	2.44 448	5.32 449	98.25 43	92.24 126	98.02 252	91.85 139	99.21 97	97.45 243

v7n		96.82 17	97.31 15	95.33 91	98.54 50	86.81 158	96.83 24	98.07 76	96.59 26	98.46 21	98.43 38	92.91 113	99.52 20	96.25 20	99.76 10	99.65 11

CP-MVS		96.44 42	96.08 59	97.54 15	98.29 72	94.62 18	96.80 26	98.08 73	92.67 93	95.08 192	96.39 194	94.77 66	99.42 38	93.17 100	99.44 52	98.58 129

COLMAP_ROB	91.06 5	96.75 24	96.62 30	97.13 32	98.38 65	94.31 21	96.79 27	98.32 36	96.69 22	96.86 87	97.56 91	95.48 31	98.77 158	90.11 194	99.44 52	98.31 155
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 33	97.05 21	95.24 97	99.02 13	86.44 170	96.78 28	98.08 73	97.42 13	98.48 20	97.86 71	91.76 140	99.63 8	94.23 59	99.84 3	99.66 9

FE-MVS		89.06 292	88.29 300	91.36 269	94.78 306	79.57 300	96.77 29	90.99 356	84.87 291	92.96 269	96.29 201	60.69 414	98.80 150	80.18 344	97.11 292	95.71 328

CS-MVS		95.77 70	95.58 87	96.37 54	96.84 174	91.72 65	96.73 30	99.06 8	94.23 63	92.48 284	94.79 276	93.56 89	99.49 30	93.47 84	99.05 114	97.89 204

sc_t1		97.21 10	97.71 5	95.71 78	99.06 10	88.89 110	96.72 31	97.79 114	98.34 3	98.97 3	99.40 5	96.81 9	98.79 151	92.58 119	99.72 15	99.45 23

tt0320-xc		97.00 13	97.67 6	94.98 107	98.89 22	86.94 155	96.72 31	98.46 22	98.28 5	98.86 8	99.43 4	96.80 10	98.51 197	91.79 141	99.76 10	99.50 19

pmmvs6		96.80 20	97.36 14	95.15 103	99.12 8	87.82 135	96.68 33	97.86 104	96.10 37	98.14 31	99.28 8	97.94 3	98.21 228	91.38 157	99.69 17	99.42 24

mvsmamba		90.24 264	89.43 278	92.64 220	95.52 284	82.36 250	96.64 34	92.29 336	81.77 328	92.14 300	96.28 203	70.59 366	99.10 104	84.44 301	95.22 349	96.47 292

3Dnovator	92.54 3	94.80 115	94.90 116	94.47 139	95.47 286	87.06 149	96.63 35	97.28 162	91.82 124	94.34 217	97.41 104	90.60 171	98.65 180	92.47 122	98.11 236	97.70 226

PS-CasMVS		96.69 28	97.43 10	94.49 138	99.13 6	84.09 220	96.61 36	97.97 93	97.91 9	98.64 17	98.13 46	95.24 44	99.65 5	93.39 91	99.84 3	99.72 4

mvs_tets		96.83 16	96.71 26	97.17 31	98.83 28	92.51 52	96.58 37	97.61 127	87.57 232	98.80 11	98.90 14	96.50 12	99.59 14	96.15 21	99.47 45	99.40 27

PEN-MVS		96.69 28	97.39 13	94.61 128	99.16 4	84.50 209	96.54 38	98.05 80	98.06 8	98.64 17	98.25 43	95.01 57	99.65 5	92.95 108	99.83 5	99.68 7

MVSMamba_PlusPlus		94.82 114	95.89 71	91.62 260	97.82 110	78.88 315	96.52 39	97.60 129	97.14 17	94.23 218	98.48 35	87.01 230	99.71 3	95.43 37	98.80 155	96.28 301

DTE-MVSNet		96.74 25	97.43 10	94.67 125	99.13 6	84.68 208	96.51 40	97.94 99	98.14 7	98.67 16	98.32 40	95.04 54	99.69 4	93.27 96	99.82 7	99.62 13

XVS		96.49 37	96.18 52	97.44 20	98.56 45	93.99 30	96.50 41	97.95 96	94.58 56	94.38 215	96.49 182	94.56 73	99.39 54	93.57 76	99.05 114	98.93 77

X-MVStestdata		90.70 246	88.45 295	97.44 20	98.56 45	93.99 30	96.50 41	97.95 96	94.58 56	94.38 215	26.89 446	94.56 73	99.39 54	93.57 76	99.05 114	98.93 77

mmtdpeth		95.82 68	96.02 64	95.23 98	96.91 168	88.62 116	96.49 43	99.26 4	95.07 50	93.41 243	99.29 7	90.25 177	97.27 313	94.49 51	99.01 121	99.80 3

EC-MVSNet		95.44 82	95.62 85	94.89 113	96.93 167	87.69 137	96.48 44	99.14 7	93.93 70	92.77 275	94.52 288	93.95 86	99.49 30	93.62 75	99.22 96	97.51 240

mPP-MVS		96.46 39	96.05 61	97.69 6	98.62 39	94.65 17	96.45 45	97.74 118	92.59 94	95.47 164	96.68 174	94.50 75	99.42 38	93.10 102	99.26 89	98.99 64

QAPM		92.88 191	92.77 192	93.22 195	95.82 264	83.31 229	96.45 45	97.35 154	83.91 301	93.75 234	96.77 163	89.25 193	98.88 133	84.56 299	97.02 295	97.49 241

jajsoiax		96.59 35	96.42 37	97.12 33	98.76 34	92.49 53	96.44 47	97.42 145	86.96 244	98.71 14	98.72 22	95.36 38	99.56 18	95.92 24	99.45 49	99.32 32

Gipuma		95.31 93	95.80 79	93.81 168	97.99 101	90.91 74	96.42 48	97.95 96	96.69 22	91.78 306	98.85 17	91.77 138	95.49 376	91.72 145	99.08 110	95.02 353
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MSP-MVS		95.34 89	94.63 134	97.48 18	98.67 36	94.05 27	96.41 49	98.18 55	91.26 146	95.12 188	95.15 258	86.60 240	99.50 24	93.43 90	96.81 305	98.89 84
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 15	96.60 32	97.56 14	98.07 88	95.27 10	96.37 50	98.12 66	95.66 43	97.00 80	97.03 145	94.85 64	99.42 38	93.49 81	98.84 144	98.00 186

RE-MVS-def			96.66 27		98.07 88	95.27 10	96.37 50	98.12 66	95.66 43	97.00 80	97.03 145	95.40 35		93.49 81	98.84 144	98.00 186

TSAR-MVS + MP.		94.96 108	94.75 124	95.57 83	98.86 26	88.69 113	96.37 50	96.81 197	85.23 281	94.75 205	97.12 137	91.85 135	99.40 51	93.45 86	98.33 214	98.62 126
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 90	95.10 111	95.96 62	96.86 172	90.75 80	96.33 53	99.20 5	93.99 67	91.03 319	93.73 314	93.52 91	99.55 19	91.81 140	99.45 49	97.58 234

ACMH	88.36 12	96.59 35	97.43 10	94.07 154	98.56 45	85.33 200	96.33 53	98.30 39	94.66 55	98.72 12	98.30 41	97.51 5	98.00 255	94.87 46	99.59 30	98.86 87
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
region2R		96.41 44	96.09 57	97.38 26	98.62 39	93.81 39	96.32 55	97.96 94	92.26 103	95.28 178	96.57 180	95.02 56	99.41 44	93.63 74	99.11 108	98.94 75

testf1		96.77 22	96.49 34	97.60 10	99.01 15	96.70 4	96.31 56	98.33 34	94.96 51	97.30 63	97.93 61	96.05 20	97.90 262	89.32 211	99.23 93	98.19 168

APD_test2		96.77 22	96.49 34	97.60 10	99.01 15	96.70 4	96.31 56	98.33 34	94.96 51	97.30 63	97.93 61	96.05 20	97.90 262	89.32 211	99.23 93	98.19 168

APD-MVS_3200maxsize		96.82 17	96.65 28	97.32 29	97.95 102	93.82 37	96.31 56	98.25 43	95.51 45	96.99 82	97.05 144	95.63 27	99.39 54	93.31 93	98.88 139	98.75 102

CP-MVSNet		96.19 53	96.80 24	94.38 143	98.99 18	83.82 223	96.31 56	97.53 137	97.60 11	98.34 23	97.52 96	91.98 133	99.63 8	93.08 104	99.81 8	99.70 5

HFP-MVS		96.39 46	96.17 54	97.04 35	98.51 53	93.37 43	96.30 60	97.98 91	92.35 100	95.63 156	96.47 183	95.37 36	99.27 83	93.78 70	99.14 106	98.48 139

ACMMPR		96.46 39	96.14 55	97.41 24	98.60 42	93.82 37	96.30 60	97.96 94	92.35 100	95.57 159	96.61 178	94.93 62	99.41 44	93.78 70	99.15 105	99.00 62

3Dnovator+	92.74 2	95.86 67	95.77 80	96.13 57	96.81 177	90.79 78	96.30 60	97.82 109	96.13 36	94.74 206	97.23 126	91.33 148	99.16 93	93.25 97	98.30 217	98.46 140

MIMVSNet1		95.52 79	95.45 91	95.72 77	99.14 5	89.02 107	96.23 63	96.87 193	93.73 74	97.87 36	98.49 34	90.73 168	99.05 110	86.43 274	99.60 28	99.10 55

balanced_conf03		93.45 170	94.17 152	91.28 274	95.81 266	78.40 322	96.20 64	97.48 142	88.56 207	95.29 177	97.20 131	85.56 254	99.21 87	92.52 121	98.91 136	96.24 304

test2506		85.42 352	84.57 355	87.96 355	97.81 111	66.53 416	96.14 65	56.35 449	89.04 193	93.55 240	98.10 47	42.88 446	98.68 175	88.09 242	99.18 101	98.67 115

SR-MVS		96.70 27	96.42 37	97.54 15	98.05 90	94.69 15	96.13 66	98.07 76	95.17 49	96.82 91	96.73 170	95.09 53	99.43 37	92.99 107	98.71 170	98.50 136

mamv4		98.21 2	97.86 3	99.26 1	98.24 78	99.36 1	96.10 67	99.32 2	98.75 2	99.58 2	98.70 23	91.78 137	99.88 1	98.60 1	99.67 23	98.54 132

MP-MVS		96.14 54	95.68 83	97.51 17	98.81 31	94.06 25	96.10 67	97.78 116	92.73 90	93.48 241	96.72 171	94.23 80	99.42 38	91.99 134	99.29 82	99.05 59
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 51	97.07 34	98.80 33	92.79 50	96.08 69	98.16 62	91.74 129	95.34 173	96.36 197	95.68 25	99.44 34	94.41 55	99.28 87	98.97 70

FA-MVS(test-final)		91.81 224	91.85 222	91.68 258	94.95 299	79.99 289	96.00 70	93.44 314	87.80 225	94.02 227	97.29 118	77.60 326	98.45 206	88.04 244	97.49 277	96.61 284

GBi-Net		93.21 181	92.96 187	93.97 157	95.40 288	84.29 213	95.99 71	96.56 216	88.63 203	95.10 189	98.53 31	81.31 295	98.98 118	86.74 264	98.38 207	98.65 117

test1		93.21 181	92.96 187	93.97 157	95.40 288	84.29 213	95.99 71	96.56 216	88.63 203	95.10 189	98.53 31	81.31 295	98.98 118	86.74 264	98.38 207	98.65 117

FMVSNet1		94.84 112	95.13 109	93.97 157	97.60 128	84.29 213	95.99 71	96.56 216	92.38 97	97.03 79	98.53 31	90.12 181	98.98 118	88.78 230	99.16 104	98.65 117

RPSCF		95.58 78	94.89 117	97.62 9	97.58 130	96.30 8	95.97 74	97.53 137	92.42 96	93.41 243	97.78 73	91.21 153	97.77 281	91.06 161	97.06 293	98.80 96

SixPastTwentyTwo		94.91 109	95.21 106	93.98 156	98.52 52	83.19 234	95.93 75	94.84 281	94.86 54	98.49 19	98.74 21	81.45 293	99.60 10	94.69 48	99.39 61	99.15 46

ambc				92.98 201	96.88 170	83.01 239	95.92 76	96.38 226		96.41 111	97.48 102	88.26 205	97.80 276	89.96 199	98.93 133	98.12 175

FC-MVSNet-test		95.32 90	95.88 72	93.62 176	98.49 60	81.77 257	95.90 77	98.32 36	93.93 70	97.53 51	97.56 91	88.48 200	99.40 51	92.91 109	99.83 5	99.68 7

reproduce_model		97.35 5	97.24 16	97.70 5	98.44 62	95.08 12	95.88 78	98.50 19	96.62 25	98.27 24	97.93 61	94.57 72	99.50 24	95.57 32	99.35 66	98.52 135

MTAPA		96.65 30	96.38 41	97.47 19	98.95 20	94.05 27	95.88 78	97.62 125	94.46 60	96.29 120	96.94 151	93.56 89	99.37 63	94.29 58	99.42 54	98.99 64

CPTT-MVS		94.74 116	94.12 154	96.60 47	98.15 83	93.01 46	95.84 80	97.66 122	89.21 192	93.28 251	95.46 247	88.89 195	98.98 118	89.80 201	98.82 150	97.80 217

ab-mvs		92.40 210	92.62 200	91.74 254	97.02 160	81.65 261	95.84 80	95.50 262	86.95 245	92.95 270	97.56 91	90.70 169	97.50 298	79.63 352	97.43 281	96.06 312

nrg030		96.32 48	96.55 33	95.62 81	97.83 109	88.55 121	95.77 82	98.29 42	92.68 91	98.03 35	97.91 68	95.13 49	98.95 126	93.85 68	99.49 44	99.36 30

ECVR-MVS		90.12 268	90.16 263	90.00 318	97.81 111	72.68 387	95.76 83	78.54 438	89.04 193	95.36 172	98.10 47	70.51 367	98.64 181	87.10 260	99.18 101	98.67 115

SteuartSystems-ACMMP		96.40 45	96.30 46	96.71 44	98.63 38	91.96 59	95.70 84	98.01 88	93.34 84	96.64 101	96.57 180	94.99 58	99.36 64	93.48 83	99.34 70	98.82 92
Skip Steuart: Steuart Systems R&D Blog.
OpenMVS	89.45 8	92.27 216	92.13 215	92.68 219	94.53 318	84.10 219	95.70 84	97.03 179	82.44 322	91.14 318	96.42 188	88.47 201	98.38 212	85.95 279	97.47 279	95.55 337

GST-MVS		96.24 51	95.99 65	97.00 37	98.65 37	92.71 51	95.69 86	98.01 88	92.08 110	95.74 151	96.28 203	95.22 46	99.42 38	93.17 100	99.06 111	98.88 86

ACMH+	88.43 11	96.48 38	96.82 23	95.47 86	98.54 50	89.06 106	95.65 87	98.61 15	96.10 37	98.16 30	97.52 96	96.90 7	98.62 182	90.30 185	99.60 28	98.72 107

APD_test1		95.91 63	95.42 94	97.36 27	98.82 29	96.62 7	95.64 88	97.64 123	93.38 83	95.89 143	97.23 126	93.35 97	97.66 291	88.20 237	98.66 178	97.79 218

sasdasda		94.59 123	94.69 128	94.30 144	95.60 280	87.03 150	95.59 89	98.24 46	91.56 135	95.21 184	92.04 356	94.95 59	98.66 177	91.45 154	97.57 274	97.20 260

test1111		90.39 257	90.61 254	89.74 322	98.04 93	71.50 393	95.59 89	79.72 435	89.41 185	95.94 139	98.14 45	70.79 365	98.81 147	88.52 235	99.32 76	98.90 83

canonicalmvs		94.59 123	94.69 128	94.30 144	95.60 280	87.03 150	95.59 89	98.24 46	91.56 135	95.21 184	92.04 356	94.95 59	98.66 177	91.45 154	97.57 274	97.20 260

SF-MVS		95.88 66	95.88 72	95.87 72	98.12 84	89.65 92	95.58 92	98.56 18	91.84 121	96.36 114	96.68 174	94.37 79	99.32 74	92.41 124	99.05 114	98.64 122

reproduce-ours		97.28 8	97.19 18	97.57 12	98.37 67	94.84 13	95.57 93	98.40 28	96.36 32	98.18 28	97.78 73	95.47 32	99.50 24	95.26 42	99.33 72	98.36 148

our_new_method		97.28 8	97.19 18	97.57 12	98.37 67	94.84 13	95.57 93	98.40 28	96.36 32	98.18 28	97.78 73	95.47 32	99.50 24	95.26 42	99.33 72	98.36 148

PS-MVSNAJss		96.01 58	96.04 62	95.89 71	98.82 29	88.51 122	95.57 93	97.88 102	88.72 201	98.81 10	98.86 15	90.77 164	99.60 10	95.43 37	99.53 40	99.57 16

PMVS	87.21 14	94.97 107	95.33 101	93.91 162	98.97 19	97.16 3	95.54 96	95.85 247	96.47 28	93.40 246	97.46 103	95.31 41	95.47 377	86.18 278	98.78 159	89.11 424
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
VDDNet		94.03 153	94.27 149	93.31 191	98.87 25	82.36 250	95.51 97	91.78 349	97.19 16	96.32 117	98.60 28	84.24 263	98.75 159	87.09 261	98.83 149	98.81 94

pm-mvs1		95.43 83	95.94 67	93.93 161	98.38 65	85.08 204	95.46 98	97.12 174	91.84 121	97.28 65	98.46 36	95.30 42	97.71 288	90.17 192	99.42 54	98.99 64

RRT-MVS		92.28 214	93.01 186	90.07 314	94.06 329	73.01 383	95.36 99	97.88 102	92.24 105	95.16 186	97.52 96	78.51 320	99.29 77	90.55 174	95.83 331	97.92 200

Vis-MVSNet		95.50 80	95.48 90	95.56 84	98.11 85	89.40 99	95.35 100	98.22 50	92.36 99	94.11 220	98.07 49	92.02 131	99.44 34	93.38 92	97.67 269	97.85 210
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test0726					98.51 53	86.69 162	95.34 101	98.18 55	91.85 118	97.63 44	97.37 107	95.58 28

FIs		94.90 110	95.35 98	93.55 180	98.28 73	81.76 258	95.33 102	98.14 63	93.05 89	97.07 75	97.18 132	87.65 218	99.29 77	91.72 145	99.69 17	99.61 14

PGM-MVS		96.32 48	95.94 67	97.43 22	98.59 44	93.84 36	95.33 102	98.30 39	91.40 143	95.76 148	96.87 156	95.26 43	99.45 33	92.77 110	99.21 97	99.00 62

LPG-MVS_test		96.38 47	96.23 49	96.84 42	98.36 70	92.13 56	95.33 102	98.25 43	91.78 125	97.07 75	97.22 128	96.38 16	99.28 81	92.07 131	99.59 30	99.11 52

MonoMVSNet		88.46 308	89.28 279	85.98 384	90.52 403	70.07 402	95.31 105	94.81 284	88.38 210	93.47 242	96.13 214	73.21 354	95.07 386	82.61 316	89.12 423	92.81 404

Elysia		96.00 59	96.36 42	94.91 111	98.01 96	85.96 184	95.29 106	97.90 100	95.31 46	98.14 31	97.28 120	88.82 196	99.51 21	97.08 6	99.38 62	99.26 35

StellarMVS		96.00 59	96.36 42	94.91 111	98.01 96	85.96 184	95.29 106	97.90 100	95.31 46	98.14 31	97.28 120	88.82 196	99.51 21	97.08 6	99.38 62	99.26 35

AllTest		94.88 111	94.51 139	96.00 59	98.02 94	92.17 54	95.26 108	98.43 25	90.48 166	95.04 193	96.74 168	92.54 122	97.86 270	85.11 291	98.98 123	97.98 190

MGCFI-Net		94.44 131	94.67 132	93.75 170	95.56 282	85.47 197	95.25 109	98.24 46	91.53 137	95.04 193	92.21 351	94.94 61	98.54 193	91.56 152	97.66 270	97.24 258

SED-MVS		96.00 59	96.41 40	94.76 119	98.51 53	86.97 152	95.21 110	98.10 70	91.95 112	97.63 44	97.25 123	96.48 13	99.35 65	93.29 94	99.29 82	97.95 195

OPU-MVS				95.15 103	96.84 174	89.43 97	95.21 110				95.66 239	93.12 105	98.06 245	86.28 277	98.61 181	97.95 195

DVP-MVS		95.82 68	96.18 52	94.72 121	98.51 53	86.69 162	95.20 112	97.00 181	91.85 118	97.40 60	97.35 113	95.58 28	99.34 68	93.44 87	99.31 77	98.13 174
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				94.88 114	98.55 48	86.72 161	95.20 112	98.22 50					99.38 61	93.44 87	99.31 77	98.53 134

Anonymous20240529		95.50 80	95.83 76	94.50 136	97.33 145	85.93 186	95.19 114	96.77 201	96.64 24	97.61 47	98.05 50	93.23 101	98.79 151	88.60 234	99.04 119	98.78 98

SMA-MVS		95.77 70	95.54 88	96.47 53	98.27 74	91.19 70	95.09 115	97.79 114	86.48 251	97.42 58	97.51 100	94.47 78	99.29 77	93.55 78	99.29 82	98.93 77
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 94	95.28 104	95.26 95	97.75 115	87.21 145	95.08 116	97.37 148	93.92 72	97.65 43	95.90 223	90.10 183	99.33 73	90.11 194	99.66 24	99.26 35

TransMVSNet (Re)		95.27 97	96.04 62	92.97 202	98.37 67	81.92 256	95.07 117	96.76 202	93.97 69	97.77 39	98.57 29	95.72 24	97.90 262	88.89 228	99.23 93	99.08 56

UGNet		93.08 184	92.50 205	94.79 118	93.87 334	87.99 131	95.07 117	94.26 297	90.64 162	87.33 385	97.67 83	86.89 235	98.49 199	88.10 241	98.71 170	97.91 201
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		89.81 279	88.90 289	92.55 229	97.00 162	79.73 297	95.03 119	83.65 417	89.88 177	95.30 175	94.79 276	53.64 425	99.39 54	91.99 134	98.79 158	98.54 132

LFMVS		91.33 237	91.16 240	91.82 251	96.27 228	79.36 304	95.01 120	85.61 404	96.04 40	94.82 202	97.06 143	72.03 361	98.46 205	84.96 294	98.70 172	97.65 230

CSCG		94.69 120	94.75 124	94.52 135	97.55 132	87.87 133	95.01 120	97.57 132	92.68 91	96.20 128	93.44 322	91.92 134	98.78 155	89.11 222	99.24 92	96.92 272

GG-mvs-BLEND				83.24 408	85.06 442	71.03 395	94.99 122	65.55 447		74.09 441	75.51 441	44.57 439	94.46 394	59.57 437	87.54 428	84.24 434

EU-MVSNet		87.39 330	86.71 335	89.44 326	93.40 341	76.11 355	94.93 123	90.00 365	57.17 441	95.71 154	97.37 107	64.77 395	97.68 290	92.67 115	94.37 369	94.52 369

KD-MVS_self_test		94.10 151	94.73 127	92.19 239	97.66 126	79.49 302	94.86 124	97.12 174	89.59 183	96.87 86	97.65 85	90.40 175	98.34 218	89.08 223	99.35 66	98.75 102

MTMP							94.82 125	54.62 450

PHI-MVS		94.34 138	93.80 162	95.95 63	95.65 276	91.67 66	94.82 125	97.86 104	87.86 224	93.04 265	94.16 299	91.58 142	98.78 155	90.27 187	98.96 130	97.41 246

gg-mvs-nofinetune		82.10 384	81.02 386	85.34 390	87.46 431	71.04 394	94.74 127	67.56 445	96.44 29	79.43 435	98.99 11	45.24 437	96.15 360	67.18 424	92.17 409	88.85 425

ACMM	88.83 9	96.30 50	96.07 60	96.97 38	98.39 64	92.95 48	94.74 127	98.03 85	90.82 157	97.15 71	96.85 157	96.25 18	99.00 117	93.10 102	99.33 72	98.95 74
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SymmetryMVS		93.26 177	92.36 209	95.97 61	97.13 156	90.84 77	94.70 129	91.61 352	90.98 152	93.22 257	95.73 236	78.94 313	99.12 100	90.38 179	98.53 190	97.97 193

SD-MVS		95.19 99	95.73 81	93.55 180	96.62 193	88.88 112	94.67 130	98.05 80	91.26 146	97.25 67	96.40 190	95.42 34	94.36 397	92.72 114	99.19 99	97.40 249
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		91.52 233	91.61 226	91.26 275	94.16 324	86.26 176	94.66 131	94.82 282	91.17 149	92.13 301	91.08 370	90.03 186	97.06 328	79.09 359	97.35 285	90.45 422

v10		94.68 121	95.27 105	92.90 209	96.57 196	80.15 281	94.65 132	97.57 132	90.68 161	97.43 56	98.00 55	88.18 206	99.15 94	94.84 47	99.55 38	99.41 26

v8		94.65 122	95.29 103	92.74 216	96.65 188	79.77 296	94.59 133	97.17 169	91.86 117	97.47 55	97.93 61	88.16 207	99.08 105	94.32 56	99.47 45	99.38 28

APD-MVS		95.00 106	94.69 128	95.93 66	97.38 141	90.88 75	94.59 133	97.81 110	89.22 191	95.46 166	96.17 213	93.42 95	99.34 68	89.30 213	98.87 142	97.56 237
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
VPA-MVSNet		95.14 101	95.67 84	93.58 179	97.76 114	83.15 235	94.58 135	97.58 131	93.39 82	97.05 78	98.04 52	93.25 100	98.51 197	89.75 204	99.59 30	99.08 56

ACMMP_NAP		96.21 52	96.12 56	96.49 52	98.90 21	91.42 67	94.57 136	98.03 85	90.42 169	96.37 113	97.35 113	95.68 25	99.25 84	94.44 54	99.34 70	98.80 96

HQP_MVS		94.26 141	93.93 158	95.23 98	97.71 120	88.12 128	94.56 137	97.81 110	91.74 129	93.31 248	95.59 241	86.93 233	98.95 126	89.26 217	98.51 194	98.60 127

plane_prior2							94.56 137		91.74 129

tfpnnormal		94.27 140	94.87 118	92.48 232	97.71 120	80.88 276	94.55 139	95.41 266	93.70 75	96.67 98	97.72 79	91.40 147	98.18 232	87.45 254	99.18 101	98.36 148

XVG-ACMP-BASELINE		95.68 74	95.34 99	96.69 45	98.40 63	93.04 45	94.54 140	98.05 80	90.45 168	96.31 118	96.76 165	92.91 113	98.72 164	91.19 159	99.42 54	98.32 153

DP-MVS		95.62 75	95.84 75	94.97 108	97.16 154	88.62 116	94.54 140	97.64 123	96.94 20	96.58 105	97.32 117	93.07 108	98.72 164	90.45 176	98.84 144	97.57 235

MIMVSNet		87.13 338	86.54 339	88.89 337	96.05 248	76.11 355	94.39 142	88.51 372	81.37 332	88.27 371	96.75 167	72.38 358	95.52 374	65.71 427	95.47 340	95.03 352

K. test v3		93.37 173	93.27 182	93.66 174	98.05 90	82.62 246	94.35 143	86.62 391	96.05 39	97.51 52	98.85 17	76.59 342	99.65 5	93.21 98	98.20 229	98.73 106

Vis-MVSNet (Re-imp)		90.42 254	90.16 263	91.20 279	97.66 126	77.32 338	94.33 144	87.66 383	91.20 148	92.99 266	95.13 260	75.40 347	98.28 221	77.86 364	99.19 99	97.99 189

ANet_high		94.83 113	96.28 47	90.47 302	96.65 188	73.16 381	94.33 144	98.74 14	96.39 31	98.09 34	98.93 13	93.37 96	98.70 171	90.38 179	99.68 20	99.53 17

MM		94.41 133	94.14 153	95.22 100	95.84 262	87.21 145	94.31 146	90.92 358	94.48 59	92.80 273	97.52 96	85.27 255	99.49 30	96.58 16	99.57 36	98.97 70

test_fmvsmconf0.01_n		95.90 64	96.09 57	95.31 94	97.30 147	89.21 102	94.24 147	98.76 13	86.25 256	97.56 48	98.66 24	95.73 23	98.44 208	97.35 4	98.99 122	98.27 159

ACMP	88.15 13	95.71 73	95.43 93	96.54 49	98.17 82	91.73 64	94.24 147	98.08 73	89.46 184	96.61 103	96.47 183	95.85 22	99.12 100	90.45 176	99.56 37	98.77 101
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MAR-MVS		90.32 262	88.87 290	94.66 127	94.82 303	91.85 61	94.22 149	94.75 286	80.91 336	87.52 383	88.07 406	86.63 239	97.87 269	76.67 375	96.21 322	94.25 375
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
FMVSNet2		92.78 196	92.73 196	92.95 204	95.40 288	81.98 255	94.18 150	95.53 261	88.63 203	96.05 135	97.37 107	81.31 295	98.81 147	87.38 257	98.67 176	98.06 177

fmvsm_s_conf0.1_n_a		94.26 141	94.37 143	93.95 160	97.36 143	85.72 192	94.15 151	95.44 263	83.25 308	95.51 161	98.05 50	92.54 122	97.19 319	95.55 33	97.46 280	98.94 75

Anonymous20240521		92.86 194	93.57 173	90.74 296	96.57 196	75.50 362	94.15 151	95.60 253	89.38 186	95.90 142	97.90 70	80.39 303	97.96 259	92.60 118	99.68 20	98.75 102

GeoE		94.55 126	94.68 131	94.15 149	97.23 149	85.11 203	94.14 153	97.34 155	88.71 202	95.26 179	95.50 246	94.65 69	99.12 100	90.94 165	98.40 202	98.23 162

9.14			94.81 119		97.49 135		94.11 154	98.37 32	87.56 233	95.38 169	96.03 219	94.66 68	99.08 105	90.70 170	98.97 128

BP-MVS1		91.77 225	91.10 241	93.75 170	96.42 210	83.40 228	94.10 155	91.89 346	91.27 145	93.36 247	94.85 271	64.43 396	99.29 77	94.88 45	98.74 167	98.56 131

HPM-MVS++		95.02 105	94.39 141	96.91 41	97.88 106	93.58 41	94.09 156	96.99 183	91.05 151	92.40 289	95.22 257	91.03 160	99.25 84	92.11 128	98.69 173	97.90 202

HY-MVS	82.50 18	86.81 344	85.93 346	89.47 325	93.63 338	77.93 328	94.02 157	91.58 353	75.68 379	83.64 412	93.64 315	77.40 329	97.42 305	71.70 408	92.07 410	93.05 400

Effi-MVS+-dtu		93.90 159	92.60 202	97.77 4	94.74 309	96.67 6	94.00 158	95.41 266	89.94 175	91.93 305	92.13 354	90.12 181	98.97 123	87.68 251	97.48 278	97.67 229

Effi-MVS+		92.79 195	92.74 194	92.94 206	95.10 296	83.30 230	94.00 158	97.53 137	91.36 144	89.35 351	90.65 380	94.01 85	98.66 177	87.40 256	95.30 346	96.88 276

VDD-MVS		94.37 135	94.37 143	94.40 142	97.49 135	86.07 181	93.97 160	93.28 316	94.49 58	96.24 124	97.78 73	87.99 213	98.79 151	88.92 226	99.14 106	98.34 152

h-mvs33		92.89 190	91.99 218	95.58 82	96.97 163	90.55 82	93.94 161	94.01 303	89.23 189	93.95 229	96.19 210	76.88 338	99.14 96	91.02 162	95.71 333	97.04 268

KinetiMVS		95.09 103	95.40 95	94.15 149	97.42 140	84.35 212	93.91 162	96.69 206	94.41 61	96.67 98	97.25 123	87.67 217	99.14 96	95.78 27	98.81 152	98.97 70

EPNet		89.80 280	88.25 303	94.45 140	83.91 444	86.18 178	93.87 163	87.07 389	91.16 150	80.64 432	94.72 278	78.83 314	98.89 132	85.17 286	98.89 137	98.28 158
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvs3		92.42 209	92.40 208	92.46 234	93.80 337	87.28 143	93.86 164	97.05 178	76.86 374	96.25 123	98.66 24	82.87 276	91.26 417	95.44 36	96.83 304	98.82 92

DeepC-MVS	91.39 4	95.43 83	95.33 101	95.71 78	97.67 125	90.17 86	93.86 164	98.02 87	87.35 234	96.22 126	97.99 58	94.48 77	99.05 110	92.73 113	99.68 20	97.93 198
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		94.20 147	94.58 136	93.04 199	95.91 258	83.13 236	93.79 166	99.19 6	92.00 111	98.84 9	98.04 52	93.64 88	99.02 115	81.28 333	98.54 189	96.96 271

TranMVSNet+NR-MVSNet		96.07 57	96.26 48	95.50 85	98.26 75	87.69 137	93.75 167	97.86 104	95.96 42	97.48 54	97.14 135	95.33 40	99.44 34	90.79 167	99.76 10	99.38 28

fmvsm_s_conf0.1_n		94.19 149	94.41 140	93.52 185	97.22 151	84.37 210	93.73 168	95.26 270	84.45 296	95.76 148	98.00 55	91.85 135	97.21 316	95.62 29	97.82 261	98.98 68

PAPM_NR		91.03 241	90.81 249	91.68 258	96.73 182	81.10 272	93.72 169	96.35 227	88.19 215	88.77 362	92.12 355	85.09 258	97.25 314	82.40 321	93.90 381	96.68 283

baseline		94.26 141	94.80 120	92.64 220	96.08 246	80.99 274	93.69 170	98.04 84	90.80 158	94.89 200	96.32 199	93.19 102	98.48 203	91.68 147	98.51 194	98.43 143

dcpmvs_2		93.96 156	95.01 114	90.82 294	97.60 128	74.04 376	93.68 171	98.85 10	89.80 179	97.82 37	97.01 148	91.14 158	99.21 87	90.56 173	98.59 184	99.19 43

GDP-MVS		91.56 231	90.83 248	93.77 169	96.34 219	83.65 225	93.66 172	98.12 66	87.32 236	92.98 268	94.71 279	63.58 402	99.30 76	92.61 117	98.14 233	98.35 151

fmvsm_s_conf0.5_n_a		94.02 154	94.08 156	93.84 166	96.72 184	85.73 191	93.65 173	95.23 271	83.30 306	95.13 187	97.56 91	92.22 127	97.17 320	95.51 34	97.41 282	98.64 122

F-COLMAP		92.28 214	91.06 242	95.95 63	97.52 133	91.90 60	93.53 174	97.18 168	83.98 300	88.70 364	94.04 302	88.41 203	98.55 192	80.17 345	95.99 326	97.39 250

test_fmvsmconf0.1_n		95.61 76	95.72 82	95.26 95	96.85 173	89.20 103	93.51 175	98.60 16	85.68 271	97.42 58	98.30 41	95.34 39	98.39 209	96.85 10	98.98 123	98.19 168

FMVSNet5		87.82 319	86.56 338	91.62 260	92.31 365	79.81 295	93.49 176	94.81 284	83.26 307	91.36 312	96.93 152	52.77 427	97.49 300	76.07 381	98.03 244	97.55 238

DPE-MVS		95.89 65	95.88 72	95.92 68	97.93 103	89.83 90	93.46 177	98.30 39	92.37 98	97.75 40	96.95 150	95.14 48	99.51 21	91.74 143	99.28 87	98.41 145
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
alignmvs		93.26 177	92.85 191	94.50 136	95.70 272	87.45 140	93.45 178	95.76 248	91.58 134	95.25 181	92.42 349	81.96 290	98.72 164	91.61 148	97.87 259	97.33 254

test_fmvsmvis_n_1920		95.08 104	95.40 95	94.13 152	96.66 187	87.75 136	93.44 179	98.49 21	85.57 275	98.27 24	97.11 138	94.11 84	97.75 284	96.26 19	98.72 168	96.89 274

114514_t		90.51 251	89.80 272	92.63 223	98.00 98	82.24 252	93.40 180	97.29 160	65.84 432	89.40 350	94.80 275	86.99 231	98.75 159	83.88 306	98.61 181	96.89 274

fmvsm_s_conf0.5_n		94.00 155	94.20 151	93.42 189	96.69 185	84.37 210	93.38 181	95.13 273	84.50 295	95.40 168	97.55 95	91.77 138	97.20 317	95.59 30	97.79 262	98.69 114

LuminaMVS		93.43 171	93.18 184	94.16 148	97.32 146	85.29 201	93.36 182	93.94 305	88.09 218	97.12 73	96.43 186	80.11 304	98.98 118	93.53 79	98.76 162	98.21 164

DeepC-MVS_fast	89.96 7	93.73 162	93.44 177	94.60 131	96.14 240	87.90 132	93.36 182	97.14 171	85.53 276	93.90 232	95.45 248	91.30 150	98.59 187	89.51 207	98.62 180	97.31 255
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 56	95.92 70	96.57 48	99.06 10	91.21 69	93.25 184	98.32 36	87.89 223	96.86 87	97.38 106	95.55 30	99.39 54	95.47 35	99.47 45	99.11 52
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_0402		95.73 72	96.22 50	94.26 146	98.19 81	85.77 190	93.24 185	97.24 165	96.88 21	97.69 42	97.77 77	94.12 83	99.13 99	91.54 153	99.29 82	97.88 205

test_fmvsmconf_n		95.43 83	95.50 89	95.22 100	96.48 207	89.19 104	93.23 186	98.36 33	85.61 274	96.92 85	98.02 54	95.23 45	98.38 212	96.69 13	98.95 132	98.09 176

test_fmvsm_n_1920		94.72 117	94.74 126	94.67 125	96.30 225	88.62 116	93.19 187	98.07 76	85.63 273	97.08 74	97.35 113	90.86 161	97.66 291	95.70 28	98.48 197	97.74 224

sd_testset		93.94 157	94.39 141	92.61 226	97.93 103	83.24 231	93.17 188	95.04 275	93.65 79	95.51 161	98.63 26	94.49 76	95.89 369	81.72 328	99.35 66	98.70 111

fmvsm_s_conf0.5_n_3		95.20 98	95.95 66	92.94 206	96.60 194	82.18 253	93.13 189	98.39 30	91.44 141	97.16 70	97.68 81	93.03 110	97.82 273	97.54 3	98.63 179	98.81 94

MSLP-MVS++		93.25 180	93.88 159	91.37 268	96.34 219	82.81 242	93.11 190	97.74 118	89.37 187	94.08 222	95.29 256	90.40 175	96.35 357	90.35 182	98.25 222	94.96 354

baseline1		87.62 324	87.31 319	88.54 344	94.71 312	74.27 373	93.10 191	88.20 376	86.20 258	92.18 299	93.04 331	73.21 354	95.52 374	79.32 356	85.82 431	95.83 323

fmvsm_l_conf0.5_n_3		95.19 99	95.36 97	94.68 124	96.79 180	87.49 139	93.05 192	98.38 31	87.21 238	96.59 104	97.76 78	94.20 81	98.11 240	95.90 25	98.40 202	98.42 144

plane_prior						88.12 128	93.01 193		88.98 195						98.06 241

guyue		92.60 203	92.62 200	92.52 231	96.73 182	81.00 273	93.00 194	91.83 348	88.28 213	96.38 112	96.23 208	80.71 301	98.37 216	92.06 133	98.37 212	98.20 166

thres100view900		87.35 331	86.89 331	88.72 340	96.14 240	73.09 382	93.00 194	85.31 407	92.13 109	93.26 253	90.96 373	63.42 403	98.28 221	71.27 411	96.54 314	94.79 362

Patchmtry		90.11 269	89.92 269	90.66 298	90.35 407	77.00 342	92.96 196	92.81 323	90.25 172	94.74 206	96.93 152	67.11 378	97.52 297	85.17 286	98.98 123	97.46 242

LF4IMVS		92.72 199	92.02 217	94.84 116	95.65 276	91.99 58	92.92 197	96.60 212	85.08 287	92.44 287	93.62 317	86.80 236	96.35 357	86.81 263	98.25 222	96.18 307

UniMVSNet (Re)		95.32 90	95.15 108	95.80 74	97.79 113	88.91 109	92.91 198	98.07 76	93.46 81	96.31 118	95.97 222	90.14 180	99.34 68	92.11 128	99.64 26	99.16 45

TAPA-MVS	88.58 10	92.49 207	91.75 225	94.73 120	96.50 204	89.69 91	92.91 198	97.68 121	78.02 365	92.79 274	94.10 300	90.85 162	97.96 259	84.76 297	98.16 231	96.54 285
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
AstraMVS		92.75 198	92.73 196	92.79 214	97.02 160	81.48 266	92.88 200	90.62 362	87.99 220	96.48 107	96.71 172	82.02 288	98.48 203	92.44 123	98.46 199	98.40 146

MVS_0304		92.88 191	92.27 210	94.69 123	92.35 364	86.03 182	92.88 200	89.68 366	90.53 165	91.52 309	96.43 186	82.52 283	99.32 74	95.01 44	99.54 39	98.71 110

fmvsm_s_conf0.5_n_5		94.50 128	94.80 120	93.60 177	96.80 178	84.93 205	92.81 202	97.59 130	85.27 280	96.85 90	97.29 118	91.48 146	98.05 246	96.67 14	98.47 198	97.83 212

thisisatest0530		88.69 305	87.52 317	92.20 238	96.33 221	79.36 304	92.81 202	84.01 416	86.44 252	93.67 237	92.68 342	53.62 426	99.25 84	89.65 206	98.45 200	98.00 186

EIA-MVS		92.35 212	92.03 216	93.30 193	95.81 266	83.97 221	92.80 204	98.17 59	87.71 228	89.79 344	87.56 408	91.17 157	99.18 92	87.97 246	97.27 286	96.77 280

thres600view7		87.66 322	87.10 328	89.36 329	96.05 248	73.17 380	92.72 205	85.31 407	91.89 116	93.29 250	90.97 372	63.42 403	98.39 209	73.23 399	96.99 300	96.51 287

wuyk23d		87.83 318	90.79 250	78.96 421	90.46 406	88.63 115	92.72 205	90.67 361	91.65 133	98.68 15	97.64 86	96.06 19	77.53 443	59.84 436	99.41 59	70.73 441

fmvsm_s_conf0.5_n_6		94.14 150	94.54 138	92.95 204	96.51 203	82.74 244	92.71 207	98.13 64	86.56 250	96.44 109	96.85 157	88.51 199	98.05 246	96.03 22	99.09 109	98.06 177

test_fmvs2		90.62 250	90.40 260	91.29 273	91.93 380	85.46 198	92.70 208	96.48 222	74.44 389	94.91 199	97.59 89	75.52 346	90.57 420	93.44 87	96.56 313	97.84 211

V42		93.43 171	93.58 172	92.97 202	95.34 292	81.22 270	92.67 209	96.49 221	87.25 237	96.20 128	96.37 196	87.32 224	98.85 139	92.39 125	98.21 227	98.85 90

casdiffmvs_mvg		95.10 102	95.62 85	93.53 183	96.25 231	83.23 232	92.66 210	98.19 53	93.06 88	97.49 53	97.15 134	94.78 65	98.71 170	92.27 126	98.72 168	98.65 117
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 76	95.45 91	96.08 58	98.49 60	91.00 72	92.65 211	97.33 156	90.05 174	96.77 94	96.85 157	95.04 54	98.56 190	92.77 110	99.06 111	98.70 111
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
fmvsm_s_conf0.5_n_8		94.70 119	95.34 99	92.78 215	96.77 181	81.50 265	92.64 212	98.50 19	91.51 140	97.22 68	97.93 61	88.07 209	98.45 206	96.62 15	98.80 155	98.39 147

test_vis1_n		89.01 295	89.01 285	89.03 334	92.57 359	82.46 249	92.62 213	96.06 239	73.02 400	90.40 330	95.77 234	74.86 348	89.68 426	90.78 168	94.98 354	94.95 355

fmvsm_s_conf0.5_n_4		94.26 141	94.58 136	93.31 191	96.40 212	82.73 245	92.59 214	97.41 146	86.60 248	96.33 115	97.07 141	89.91 187	98.07 244	96.88 9	98.01 247	99.13 48

DU-MVS		95.28 94	95.12 110	95.75 76	97.75 115	88.59 119	92.58 215	97.81 110	93.99 67	96.80 92	95.90 223	90.10 183	99.41 44	91.60 149	99.58 34	99.26 35

FMVSNet3		90.78 244	90.32 262	92.16 243	93.03 350	79.92 291	92.54 216	94.95 278	86.17 261	95.10 189	96.01 220	69.97 369	98.75 159	86.74 264	98.38 207	97.82 215

hse-mvs2		92.24 217	91.20 237	95.38 88	96.16 237	90.65 81	92.52 217	92.01 345	89.23 189	93.95 229	92.99 333	76.88 338	98.69 173	91.02 162	96.03 324	96.81 278

MVS_Test		92.57 206	93.29 179	90.40 305	93.53 340	75.85 358	92.52 217	96.96 184	88.73 200	92.35 293	96.70 173	90.77 164	98.37 216	92.53 120	95.49 339	96.99 270

CR-MVSNet		87.89 316	87.12 327	90.22 310	91.01 396	78.93 311	92.52 217	92.81 323	73.08 399	89.10 352	96.93 152	67.11 378	97.64 293	88.80 229	92.70 403	94.08 376

RPMNet		90.31 263	90.14 266	90.81 295	91.01 396	78.93 311	92.52 217	98.12 66	91.91 115	89.10 352	96.89 155	68.84 371	99.41 44	90.17 192	92.70 403	94.08 376

fmvsm_l_conf0.5_n		93.79 160	93.81 160	93.73 172	96.16 237	86.26 176	92.46 221	96.72 204	81.69 330	95.77 147	97.11 138	90.83 163	97.82 273	95.58 31	97.99 250	97.11 263

XVG-OURS-SEG-HR		95.38 87	95.00 115	96.51 50	98.10 86	94.07 24	92.46 221	98.13 64	90.69 160	93.75 234	96.25 207	98.03 2	97.02 329	92.08 130	95.55 337	98.45 141

EI-MVSNet-Vis-set		94.36 136	94.28 147	94.61 128	92.55 360	85.98 183	92.44 223	94.69 288	93.70 75	96.12 133	95.81 229	91.24 151	98.86 137	93.76 73	98.22 226	98.98 68

Anonymous202405211		92.58 204	92.50 205	92.83 212	96.55 198	83.22 233	92.43 224	91.64 351	94.10 66	95.59 158	96.64 176	81.88 292	97.50 298	85.12 290	98.52 192	97.77 220

AUN-MVS		90.05 273	88.30 299	95.32 93	96.09 245	90.52 83	92.42 225	92.05 344	82.08 326	88.45 368	92.86 335	65.76 388	98.69 173	88.91 227	96.07 323	96.75 282

EI-MVSNet-UG-set		94.35 137	94.27 149	94.59 132	92.46 363	85.87 188	92.42 225	94.69 288	93.67 78	96.13 132	95.84 227	91.20 154	98.86 137	93.78 70	98.23 224	99.03 60

NCCC		94.08 152	93.54 175	95.70 80	96.49 205	89.90 89	92.39 227	96.91 190	90.64 162	92.33 296	94.60 284	90.58 172	98.96 124	90.21 191	97.70 267	98.23 162

casdiffmvs		94.32 139	94.80 120	92.85 211	96.05 248	81.44 267	92.35 228	98.05 80	91.53 137	95.75 150	96.80 161	93.35 97	98.49 199	91.01 164	98.32 216	98.64 122
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		92.99 187	92.74 194	93.72 173	95.86 261	86.30 175	92.33 229	97.84 107	91.70 132	92.81 272	86.17 418	92.22 127	99.19 91	88.03 245	97.73 264	95.66 332

fmvsm_l_conf0.5_n_a		93.59 166	93.63 169	93.49 187	96.10 244	85.66 194	92.32 230	96.57 215	81.32 333	95.63 156	97.14 135	90.19 178	97.73 287	95.37 40	98.03 244	97.07 264

EI-MVSNet		92.99 187	93.26 183	92.19 239	92.12 373	79.21 309	92.32 230	94.67 290	91.77 127	95.24 182	95.85 225	87.14 228	98.49 199	91.99 134	98.26 220	98.86 87

CVMVSNet		85.16 354	84.72 352	86.48 376	92.12 373	70.19 398	92.32 230	88.17 377	56.15 442	90.64 326	95.85 225	67.97 376	96.69 344	88.78 230	90.52 419	92.56 407

VortexMVS		92.13 219	92.56 203	90.85 292	94.54 317	76.17 354	92.30 233	96.63 211	86.20 258	96.66 100	96.79 162	79.87 306	98.16 234	91.27 158	98.76 162	98.24 161

test_fmvs1_n		88.73 304	88.38 297	89.76 321	92.06 375	82.53 247	92.30 233	96.59 214	71.14 410	92.58 281	95.41 253	68.55 372	89.57 428	91.12 160	95.66 334	97.18 262

OMC-MVS		94.22 146	93.69 167	95.81 73	97.25 148	91.27 68	92.27 235	97.40 147	87.10 242	94.56 210	95.42 250	93.74 87	98.11 240	86.62 268	98.85 143	98.06 177

PM-MVS		93.33 174	92.67 199	95.33 91	96.58 195	94.06 25	92.26 236	92.18 338	85.92 265	96.22 126	96.61 178	85.64 252	95.99 367	90.35 182	98.23 224	95.93 318

UniMVSNet_NR-MVSNet		95.35 88	95.21 106	95.76 75	97.69 123	88.59 119	92.26 236	97.84 107	94.91 53	96.80 92	95.78 233	90.42 173	99.41 44	91.60 149	99.58 34	99.29 34

AdaColmap		91.63 229	91.36 234	92.47 233	95.56 282	86.36 173	92.24 238	96.27 229	88.88 199	89.90 341	92.69 341	91.65 141	98.32 219	77.38 371	97.64 271	92.72 406

PVSNet_Blended_VisFu		91.63 229	91.20 237	92.94 206	97.73 118	83.95 222	92.14 239	97.46 143	78.85 361	92.35 293	94.98 266	84.16 264	99.08 105	86.36 275	96.77 307	95.79 325

Baseline_NR-MVSNet		94.47 130	95.09 112	92.60 227	98.50 59	80.82 277	92.08 240	96.68 207	93.82 73	96.29 120	98.56 30	90.10 183	97.75 284	90.10 196	99.66 24	99.24 39

Fast-Effi-MVS+-dtu		92.77 197	92.16 212	94.58 134	94.66 314	88.25 126	92.05 241	96.65 209	89.62 182	90.08 336	91.23 367	92.56 121	98.60 185	86.30 276	96.27 321	96.90 273

save fliter					97.46 138	88.05 130	92.04 242	97.08 176	87.63 231

PatchT		87.51 327	88.17 308	85.55 388	90.64 400	66.91 413	92.02 243	86.09 395	92.20 106	89.05 355	97.16 133	64.15 398	96.37 356	89.21 220	92.98 401	93.37 395

EG-PatchMatch MVS		94.54 127	94.67 132	94.14 151	97.87 108	86.50 166	92.00 244	96.74 203	88.16 217	96.93 84	97.61 88	93.04 109	97.90 262	91.60 149	98.12 235	98.03 184

fmvsm_s_conf0.1_n_2		94.38 134	94.78 123	93.19 196	97.07 159	81.72 260	91.97 245	97.51 140	87.05 243	97.31 62	97.92 66	88.29 204	98.15 236	97.10 5	98.81 152	99.70 5

v144192		93.20 183	93.54 175	92.16 243	96.05 248	78.26 325	91.95 246	97.14 171	84.98 289	95.96 137	96.11 215	87.08 229	99.04 113	93.79 69	98.84 144	99.17 44

VNet		92.67 201	92.96 187	91.79 252	96.27 228	80.15 281	91.95 246	94.98 277	92.19 107	94.52 212	96.07 217	87.43 222	97.39 308	84.83 295	98.38 207	97.83 212

1314		86.46 346	86.33 343	86.87 372	91.65 387	74.54 368	91.94 248	94.10 299	74.28 391	84.78 402	87.33 412	83.03 274	95.00 387	78.72 360	91.16 416	91.06 419

MVS		84.98 356	84.30 357	87.01 367	91.03 395	77.69 334	91.94 248	94.16 298	59.36 440	84.23 407	87.50 410	85.66 250	96.80 341	71.79 406	93.05 400	86.54 432

SDMVSNet		94.43 132	95.02 113	92.69 218	97.93 103	82.88 241	91.92 250	95.99 244	93.65 79	95.51 161	98.63 26	94.60 71	96.48 350	87.57 252	99.35 66	98.70 111

tfpn200view9		87.05 340	86.52 340	88.67 341	95.77 268	72.94 384	91.89 251	86.00 396	90.84 155	92.61 279	89.80 384	63.93 399	98.28 221	71.27 411	96.54 314	94.79 362

thres400		87.20 335	86.52 340	89.24 333	95.77 268	72.94 384	91.89 251	86.00 396	90.84 155	92.61 279	89.80 384	63.93 399	98.28 221	71.27 411	96.54 314	96.51 287

v1921920		93.26 177	93.61 171	92.19 239	96.04 252	78.31 324	91.88 253	97.24 165	85.17 283	96.19 131	96.19 210	86.76 237	99.05 110	94.18 60	98.84 144	99.22 40

XXY-MVS		92.58 204	93.16 185	90.84 293	97.75 115	79.84 292	91.87 254	96.22 234	85.94 264	95.53 160	97.68 81	92.69 119	94.48 393	83.21 310	97.51 276	98.21 164

IterMVS-LS		93.78 161	94.28 147	92.27 236	96.27 228	79.21 309	91.87 254	96.78 199	91.77 127	96.57 106	97.07 141	87.15 227	98.74 162	91.99 134	99.03 120	98.86 87
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1144		93.50 167	93.81 160	92.57 228	96.28 226	79.61 299	91.86 256	96.96 184	86.95 245	95.91 141	96.32 199	87.65 218	98.96 124	93.51 80	98.88 139	99.13 48

v1192		93.49 168	93.78 163	92.62 225	96.16 237	79.62 298	91.83 257	97.22 167	86.07 262	96.10 134	96.38 195	87.22 225	99.02 115	94.14 61	98.88 139	99.22 40

v1240		93.29 175	93.71 166	92.06 246	96.01 253	77.89 330	91.81 258	97.37 148	85.12 285	96.69 97	96.40 190	86.67 238	99.07 109	94.51 50	98.76 162	99.22 40

CNVR-MVS		94.58 125	94.29 146	95.46 87	96.94 165	89.35 101	91.81 258	96.80 198	89.66 181	93.90 232	95.44 249	92.80 117	98.72 164	92.74 112	98.52 192	98.32 153

v2v482		93.29 175	93.63 169	92.29 235	96.35 218	78.82 317	91.77 260	96.28 228	88.45 208	95.70 155	96.26 206	86.02 247	98.90 130	93.02 105	98.81 152	99.14 47

fmvsm_s_conf0.5_n_2		94.25 145	94.63 134	93.10 198	96.65 188	81.75 259	91.72 261	97.25 163	86.93 247	97.20 69	97.67 83	88.44 202	98.14 239	97.06 8	98.77 160	99.42 24

EPNet_dtu		85.63 350	84.37 356	89.40 328	86.30 436	74.33 372	91.64 262	88.26 374	84.84 292	72.96 442	89.85 382	71.27 364	97.69 289	76.60 376	97.62 272	96.18 307
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PLC	85.34 15	90.40 255	88.92 287	94.85 115	96.53 202	90.02 87	91.58 263	96.48 222	80.16 342	86.14 391	92.18 352	85.73 249	98.25 226	76.87 374	94.61 365	96.30 299
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VPNet		93.08 184	93.76 164	91.03 283	98.60 42	75.83 360	91.51 264	95.62 252	91.84 121	95.74 151	97.10 140	89.31 192	98.32 219	85.07 293	99.06 111	98.93 77

ttmdpeth		86.91 343	86.57 337	87.91 358	89.68 414	74.24 374	91.49 265	87.09 387	79.84 343	89.46 349	97.86 71	65.42 390	91.04 418	81.57 330	96.74 310	98.44 142

XVG-OURS		94.72 117	94.12 154	96.50 51	98.00 98	94.23 22	91.48 266	98.17 59	90.72 159	95.30 175	96.47 183	87.94 214	96.98 330	91.41 156	97.61 273	98.30 157

HQP-NCC					96.36 215		91.37 267		87.16 239	88.81 358

ACMP_Plane					96.36 215		91.37 267		87.16 239	88.81 358

HQP-MVS		92.09 220	91.49 231	93.88 163	96.36 215	84.89 206	91.37 267	97.31 157	87.16 239	88.81 358	93.40 323	84.76 260	98.60 185	86.55 271	97.73 264	98.14 173

MCST-MVS		92.91 189	92.51 204	94.10 153	97.52 133	85.72 192	91.36 270	97.13 173	80.33 341	92.91 271	94.24 295	91.23 152	98.72 164	89.99 198	97.93 255	97.86 208

v148		92.87 193	93.29 179	91.62 260	96.25 231	77.72 333	91.28 271	95.05 274	89.69 180	95.93 140	96.04 218	87.34 223	98.38 212	90.05 197	97.99 250	98.78 98

tpmvs		84.22 363	83.97 362	84.94 394	87.09 433	65.18 423	91.21 272	88.35 373	82.87 316	85.21 395	90.96 373	65.24 393	96.75 342	79.60 355	85.25 432	92.90 403

reproduce_monomvs		87.13 338	86.90 330	87.84 360	90.92 398	68.15 408	91.19 273	93.75 307	85.84 266	94.21 219	95.83 228	42.99 443	97.10 324	89.46 209	97.88 258	98.26 160

CANet		92.38 211	91.99 218	93.52 185	93.82 336	83.46 227	91.14 274	97.00 181	89.81 178	86.47 389	94.04 302	87.90 215	99.21 87	89.50 208	98.27 219	97.90 202

CNLPA		91.72 227	91.20 237	93.26 194	96.17 236	91.02 71	91.14 274	95.55 260	90.16 173	90.87 320	93.56 320	86.31 243	94.40 396	79.92 351	97.12 291	94.37 372

DP-MVS Recon		92.31 213	91.88 221	93.60 177	97.18 153	86.87 156	91.10 276	97.37 148	84.92 290	92.08 302	94.08 301	88.59 198	98.20 229	83.50 307	98.14 233	95.73 327

OpenMVS_ROB	85.12 16	89.52 283	89.05 283	90.92 288	94.58 316	81.21 271	91.10 276	93.41 315	77.03 373	93.41 243	93.99 306	83.23 271	97.80 276	79.93 349	94.80 360	93.74 387

MVStest1		84.79 358	84.06 361	86.98 368	77.73 449	74.76 364	91.08 278	85.63 401	77.70 366	96.86 87	97.97 59	41.05 448	88.24 433	92.22 127	96.28 320	97.94 197

TSAR-MVS + GP.		93.07 186	92.41 207	95.06 105	95.82 264	90.87 76	90.97 279	92.61 331	88.04 219	94.61 209	93.79 313	88.08 208	97.81 275	89.41 210	98.39 206	96.50 290

MVP-Stereo		90.07 272	88.92 287	93.54 182	96.31 223	86.49 167	90.93 280	95.59 257	79.80 344	91.48 310	95.59 241	80.79 299	97.39 308	78.57 362	91.19 415	96.76 281
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVSTER		89.32 287	88.75 291	91.03 283	90.10 410	76.62 349	90.85 281	94.67 290	82.27 323	95.24 182	95.79 230	61.09 412	98.49 199	90.49 175	98.26 220	97.97 193

pmmvs-eth3d		91.54 232	90.73 252	93.99 155	95.76 270	87.86 134	90.83 282	93.98 304	78.23 364	94.02 227	96.22 209	82.62 282	96.83 339	86.57 269	98.33 214	97.29 256

fmvsm_s_conf0.5_n_7		93.61 165	93.94 157	92.63 223	96.11 243	82.76 243	90.81 283	97.55 134	86.57 249	93.14 261	97.69 80	90.17 179	96.83 339	94.46 52	98.93 133	98.31 155

CANet_DTU		89.85 278	89.17 281	91.87 249	92.20 370	80.02 288	90.79 284	95.87 246	86.02 263	82.53 422	91.77 360	80.01 305	98.57 189	85.66 283	97.70 267	97.01 269

SSC-MVS		90.16 266	92.96 187	81.78 414	97.88 106	48.48 447	90.75 285	87.69 382	96.02 41	96.70 96	97.63 87	85.60 253	97.80 276	85.73 282	98.60 183	99.06 58

test_prior4						89.91 88	90.74 286

TinyColmap		92.00 222	92.76 193	89.71 323	95.62 279	77.02 341	90.72 287	96.17 237	87.70 229	95.26 179	96.29 201	92.54 122	96.45 352	81.77 326	98.77 160	95.66 332

CDPH-MVS		92.67 201	91.83 223	95.18 102	96.94 165	88.46 124	90.70 288	97.07 177	77.38 368	92.34 295	95.08 263	92.67 120	98.88 133	85.74 281	98.57 186	98.20 166

test_vis1_n_1920		89.45 284	89.85 271	88.28 350	93.59 339	76.71 348	90.67 289	97.78 116	79.67 348	90.30 333	96.11 215	76.62 341	92.17 413	90.31 184	93.57 386	95.96 316

DSMNet-mixed		82.21 381	81.56 380	84.16 402	89.57 417	70.00 403	90.65 290	77.66 440	54.99 443	83.30 416	97.57 90	77.89 325	90.50 422	66.86 425	95.54 338	91.97 411

TEST9					96.45 208	89.46 95	90.60 291	96.92 188	79.09 357	90.49 327	94.39 291	91.31 149	98.88 133

train_agg		92.71 200	91.83 223	95.35 89	96.45 208	89.46 95	90.60 291	96.92 188	79.37 352	90.49 327	94.39 291	91.20 154	98.88 133	88.66 233	98.43 201	97.72 225

PatchmatchNet		85.22 353	84.64 353	86.98 368	89.51 418	69.83 404	90.52 293	87.34 386	78.87 360	87.22 386	92.74 340	66.91 380	96.53 347	81.77 326	86.88 429	94.58 368
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_8					96.37 213	89.14 105	90.51 294	96.89 191	79.37 352	90.42 329	94.36 293	91.20 154	98.82 142

test_yl		90.11 269	89.73 275	91.26 275	94.09 327	79.82 293	90.44 295	92.65 328	90.90 153	93.19 259	93.30 325	73.90 351	98.03 249	82.23 322	96.87 302	95.93 318

DCV-MVSNet		90.11 269	89.73 275	91.26 275	94.09 327	79.82 293	90.44 295	92.65 328	90.90 153	93.19 259	93.30 325	73.90 351	98.03 249	82.23 322	96.87 302	95.93 318

tpm2		81.46 387	80.35 395	84.80 395	89.90 411	65.14 424	90.44 295	85.36 406	65.82 433	82.05 425	92.44 347	57.94 417	96.69 344	70.71 415	88.49 426	92.56 407

test_fmvs1		87.59 325	87.27 321	88.54 344	88.32 426	81.26 269	90.43 298	95.72 250	70.55 416	91.70 307	94.63 282	68.13 373	89.42 430	90.59 172	95.34 345	94.94 357

test_vis3_rt		90.40 255	90.03 267	91.52 265	92.58 358	88.95 108	90.38 299	97.72 120	73.30 397	97.79 38	97.51 100	77.05 334	87.10 435	89.03 224	94.89 356	98.50 136

CostFormer		83.09 374	82.21 377	85.73 385	89.27 420	67.01 412	90.35 300	86.47 392	70.42 417	83.52 414	93.23 328	61.18 411	96.85 338	77.21 372	88.26 427	93.34 396

TAMVS		90.16 266	89.05 283	93.49 187	96.49 205	86.37 172	90.34 301	92.55 332	80.84 339	92.99 266	94.57 287	81.94 291	98.20 229	73.51 397	98.21 227	95.90 321

EPMVS		81.17 391	80.37 394	83.58 406	85.58 439	65.08 425	90.31 302	71.34 444	77.31 371	85.80 393	91.30 366	59.38 415	92.70 411	79.99 346	82.34 438	92.96 402

CMPMVS	68.83 22	87.28 332	85.67 348	92.09 245	88.77 424	85.42 199	90.31 302	94.38 293	70.02 419	88.00 374	93.30 325	73.78 353	94.03 402	75.96 383	96.54 314	96.83 277
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_post1							90.21 304				5.85 450	65.36 391	96.00 366	79.61 353

test_prior2							90.21 304		89.33 188	90.77 322	94.81 273	90.41 174		88.21 236	98.55 187

MVS_111021_LR		93.66 163	93.28 181	94.80 117	96.25 231	90.95 73	90.21 304	95.43 265	87.91 221	93.74 236	94.40 290	92.88 115	96.38 355	90.39 178	98.28 218	97.07 264

WR-MVS		93.49 168	93.72 165	92.80 213	97.57 131	80.03 287	90.14 307	95.68 251	93.70 75	96.62 102	95.39 254	87.21 226	99.04 113	87.50 253	99.64 26	99.33 31

tpmrst		82.85 378	82.93 372	82.64 410	87.65 428	58.99 440	90.14 307	87.90 381	75.54 381	83.93 410	91.63 363	66.79 383	95.36 380	81.21 335	81.54 439	93.57 394

PVSNet_BlendedMVS		90.35 260	89.96 268	91.54 264	94.81 304	78.80 319	90.14 307	96.93 186	79.43 351	88.68 365	95.06 264	86.27 244	98.15 236	80.27 341	98.04 243	97.68 228

BH-untuned		90.68 247	90.90 244	90.05 317	95.98 254	79.57 300	90.04 310	94.94 279	87.91 221	94.07 223	93.00 332	87.76 216	97.78 280	79.19 358	95.17 350	92.80 405

新几何2							90.02 311

旧先验2							90.00 312		68.65 424	92.71 277			96.52 348	85.15 288

无先验							89.94 313	95.75 249	70.81 414				98.59 187	81.17 336		94.81 360

xiu_mvs_v1_base_debu		91.47 234	91.52 228	91.33 270	95.69 273	81.56 262	89.92 314	96.05 241	83.22 309	91.26 314	90.74 375	91.55 143	98.82 142	89.29 214	95.91 327	93.62 391

xiu_mvs_v1_base		91.47 234	91.52 228	91.33 270	95.69 273	81.56 262	89.92 314	96.05 241	83.22 309	91.26 314	90.74 375	91.55 143	98.82 142	89.29 214	95.91 327	93.62 391

xiu_mvs_v1_base_debi		91.47 234	91.52 228	91.33 270	95.69 273	81.56 262	89.92 314	96.05 241	83.22 309	91.26 314	90.74 375	91.55 143	98.82 142	89.29 214	95.91 327	93.62 391

mvs_anonymous		90.37 259	91.30 236	87.58 362	92.17 372	68.00 409	89.84 317	94.73 287	83.82 303	93.22 257	97.40 105	87.54 220	97.40 307	87.94 247	95.05 353	97.34 253

test20.03		90.80 243	90.85 247	90.63 299	95.63 278	79.24 307	89.81 318	92.87 322	89.90 176	94.39 214	96.40 190	85.77 248	95.27 384	73.86 396	99.05 114	97.39 250

testing3		83.66 369	82.52 374	87.08 366	95.84 262	65.84 421	89.80 319	77.17 442	88.17 216	90.84 321	88.63 399	30.95 451	98.11 240	84.05 304	97.19 289	97.28 257

WB-MVS		89.44 285	92.15 214	81.32 415	97.73 118	48.22 448	89.73 320	87.98 380	95.24 48	96.05 135	96.99 149	85.18 256	96.95 331	82.45 320	97.97 252	98.78 98

1112_ss		88.42 309	87.41 318	91.45 266	96.69 185	80.99 274	89.72 321	96.72 204	73.37 396	87.00 387	90.69 378	77.38 330	98.20 229	81.38 332	93.72 384	95.15 346

UnsupCasMVSNet_eth		90.33 261	90.34 261	90.28 307	94.64 315	80.24 279	89.69 322	95.88 245	85.77 268	93.94 231	95.69 238	81.99 289	92.98 410	84.21 303	91.30 414	97.62 231

MG-MVS		89.54 282	89.80 272	88.76 339	94.88 300	72.47 389	89.60 323	92.44 334	85.82 267	89.48 348	95.98 221	82.85 277	97.74 286	81.87 325	95.27 347	96.08 311

Patchmatch-test		86.10 348	86.01 345	86.38 380	90.63 401	74.22 375	89.57 324	86.69 390	85.73 270	89.81 343	92.83 336	65.24 393	91.04 418	77.82 367	95.78 332	93.88 384

Anonymous20231206		88.77 302	88.29 300	90.20 312	96.31 223	78.81 318	89.56 325	93.49 313	74.26 392	92.38 290	95.58 244	82.21 284	95.43 379	72.07 405	98.75 166	96.34 297

dmvs_re		84.69 360	83.94 363	86.95 370	92.24 367	82.93 240	89.51 326	87.37 385	84.38 298	85.37 394	85.08 426	72.44 357	86.59 436	68.05 421	91.03 418	91.33 416

DeepPCF-MVS	90.46 6	94.20 147	93.56 174	96.14 56	95.96 255	92.96 47	89.48 327	97.46 143	85.14 284	96.23 125	95.42 250	93.19 102	98.08 243	90.37 181	98.76 162	97.38 252

test_cas_vis1_n_1920		88.25 312	88.27 302	88.20 352	92.19 371	78.92 313	89.45 328	95.44 263	75.29 386	93.23 256	95.65 240	71.58 362	90.23 424	88.05 243	93.55 388	95.44 340

SCA		87.43 329	87.21 323	88.10 354	92.01 377	71.98 391	89.43 329	88.11 378	82.26 324	88.71 363	92.83 336	78.65 316	97.59 294	79.61 353	93.30 392	94.75 364

testgi		90.38 258	91.34 235	87.50 363	97.49 135	71.54 392	89.43 329	95.16 272	88.38 210	94.54 211	94.68 281	92.88 115	93.09 409	71.60 409	97.85 260	97.88 205

JIA-IIPM		85.08 355	83.04 370	91.19 280	87.56 429	86.14 179	89.40 331	84.44 415	88.98 195	82.20 423	97.95 60	56.82 420	96.15 360	76.55 378	83.45 435	91.30 417

原ACMM2							89.34 332

tpm		84.38 362	84.08 360	85.30 391	90.47 405	63.43 431	89.34 332	85.63 401	77.24 372	87.62 381	95.03 265	61.00 413	97.30 311	79.26 357	91.09 417	95.16 345

MVS_111021_HR		93.63 164	93.42 178	94.26 146	96.65 188	86.96 154	89.30 334	96.23 232	88.36 212	93.57 239	94.60 284	93.45 92	97.77 281	90.23 190	98.38 207	98.03 184

tpm cat1		80.61 396	79.46 399	84.07 403	88.78 423	65.06 426	89.26 335	88.23 375	62.27 438	81.90 427	89.66 390	62.70 408	95.29 383	71.72 407	80.60 440	91.86 414

CDS-MVSNet		89.55 281	88.22 306	93.53 183	95.37 291	86.49 167	89.26 335	93.59 309	79.76 346	91.15 317	92.31 350	77.12 333	98.38 212	77.51 369	97.92 256	95.71 328
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+		91.28 239	90.86 246	92.53 230	95.45 287	82.53 247	89.25 337	96.52 220	85.00 288	89.91 340	88.55 401	92.94 111	98.84 140	84.72 298	95.44 341	96.22 305

BH-RMVSNet		90.47 253	90.44 258	90.56 301	95.21 295	78.65 321	89.15 338	93.94 305	88.21 214	92.74 276	94.22 296	86.38 241	97.88 266	78.67 361	95.39 343	95.14 347

thres200		85.85 349	85.18 350	87.88 359	94.44 319	72.52 388	89.08 339	86.21 393	88.57 206	91.44 311	88.40 402	64.22 397	98.00 255	68.35 420	95.88 330	93.12 397

USDC		89.02 293	89.08 282	88.84 338	95.07 297	74.50 370	88.97 340	96.39 225	73.21 398	93.27 252	96.28 203	82.16 286	96.39 354	77.55 368	98.80 155	95.62 335

testdata1							88.96 341		88.44 209

pmmvs5		87.87 317	87.14 325	90.07 314	93.26 345	76.97 345	88.89 342	92.18 338	73.71 395	88.36 369	93.89 310	76.86 340	96.73 343	80.32 340	96.81 305	96.51 287

dmvs_testset		78.23 407	78.99 401	75.94 423	91.99 378	55.34 445	88.86 343	78.70 437	82.69 317	81.64 429	79.46 438	75.93 344	85.74 438	48.78 443	82.85 437	86.76 431

patch_mono-2		92.46 208	92.72 198	91.71 256	96.65 188	78.91 314	88.85 344	97.17 169	83.89 302	92.45 286	96.76 165	89.86 188	97.09 325	90.24 189	98.59 184	99.12 51

test222					96.95 164	85.27 202	88.83 345	93.61 308	65.09 434	90.74 323	94.85 271	84.62 262			97.36 284	93.91 382

baseline2		83.38 372	81.54 382	88.90 336	91.38 391	72.84 386	88.78 346	81.22 428	78.97 358	79.82 434	87.56 408	61.73 410	97.80 276	74.30 393	90.05 421	96.05 313

diffmvs		91.74 226	91.93 220	91.15 281	93.06 348	78.17 326	88.77 347	97.51 140	86.28 255	92.42 288	93.96 307	88.04 211	97.46 301	90.69 171	96.67 311	97.82 215
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			83.88 365		89.42 419	61.52 434	88.74 348	87.41 384	73.99 393	84.96 401	94.01 305	65.25 392	95.53 373	78.02 363	93.16 395

D2MVS		89.93 275	89.60 277	90.92 288	94.03 330	78.40 322	88.69 349	94.85 280	78.96 359	93.08 262	95.09 262	74.57 349	96.94 332	88.19 238	98.96 130	97.41 246

TR-MVS		87.70 320	87.17 324	89.27 331	94.11 326	79.26 306	88.69 349	91.86 347	81.94 327	90.69 325	89.79 386	82.82 278	97.42 305	72.65 403	91.98 411	91.14 418

PatchMatch-RL		89.18 288	88.02 311	92.64 220	95.90 259	92.87 49	88.67 351	91.06 355	80.34 340	90.03 338	91.67 362	83.34 269	94.42 395	76.35 379	94.84 359	90.64 421

PAPR		87.65 323	86.77 334	90.27 308	92.85 355	77.38 337	88.56 352	96.23 232	76.82 376	84.98 400	89.75 388	86.08 246	97.16 322	72.33 404	93.35 391	96.26 303

testing3-2		83.95 367	84.22 359	83.13 409	96.28 226	54.34 446	88.51 353	83.01 421	92.19 107	89.09 354	90.98 371	45.51 436	97.44 303	74.38 392	98.01 247	97.60 233

MDTV_nov1_ep13_2view						42.48 451	88.45 354		67.22 428	83.56 413		66.80 381		72.86 402		94.06 378

WB-MVSnew		84.20 364	83.89 364	85.16 393	91.62 388	66.15 420	88.44 355	81.00 429	76.23 378	87.98 375	87.77 407	84.98 259	93.35 407	62.85 434	94.10 379	95.98 315

jason		89.17 289	88.32 298	91.70 257	95.73 271	80.07 284	88.10 356	93.22 317	71.98 405	90.09 335	92.79 338	78.53 319	98.56 190	87.43 255	97.06 293	96.46 293
jason: jason.
mvsany_test3		89.11 291	88.21 307	91.83 250	91.30 393	90.25 85	88.09 357	78.76 436	76.37 377	96.43 110	98.39 39	83.79 267	90.43 423	86.57 269	94.20 374	94.80 361

BH-w/o		87.21 334	87.02 329	87.79 361	94.77 307	77.27 339	87.90 358	93.21 319	81.74 329	89.99 339	88.39 403	83.47 268	96.93 334	71.29 410	92.43 407	89.15 423

MS-PatchMatch		88.05 315	87.75 313	88.95 335	93.28 343	77.93 328	87.88 359	92.49 333	75.42 382	92.57 282	93.59 319	80.44 302	94.24 400	81.28 333	92.75 402	94.69 367

UWE-MVS-28		74.73 408	73.18 411	79.35 420	85.42 440	55.55 444	87.63 360	65.92 446	74.39 390	77.33 438	88.19 404	47.63 432	89.48 429	39.01 445	93.14 397	93.03 401

DELS-MVS		92.05 221	92.16 212	91.72 255	94.44 319	80.13 283	87.62 361	97.25 163	87.34 235	92.22 298	93.18 330	89.54 191	98.73 163	89.67 205	98.20 229	96.30 299
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		84.01 365	82.20 378	89.41 327	89.04 421	76.37 353	87.57 362	90.98 357	72.71 403	84.46 403	92.45 345	68.08 374	96.48 350	70.58 416	83.97 433	95.38 341

ADS-MVSNet		82.25 380	81.55 381	84.34 400	89.04 421	65.30 422	87.57 362	85.13 411	72.71 403	84.46 403	92.45 345	68.08 374	92.33 412	70.58 416	83.97 433	95.38 341

IterMVS-SCA-FT		91.65 228	91.55 227	91.94 248	93.89 333	79.22 308	87.56 364	93.51 312	91.53 137	95.37 171	96.62 177	78.65 316	98.90 130	91.89 138	94.95 355	97.70 226

IterMVS		90.18 265	90.16 263	90.21 311	93.15 346	75.98 357	87.56 364	92.97 321	86.43 253	94.09 221	96.40 190	78.32 321	97.43 304	87.87 248	94.69 363	97.23 259
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Test_1112_low_res		87.50 328	86.58 336	90.25 309	96.80 178	77.75 332	87.53 366	96.25 230	69.73 421	86.47 389	93.61 318	75.67 345	97.88 266	79.95 347	93.20 394	95.11 350

c3_l		91.32 238	91.42 232	91.00 286	92.29 366	76.79 347	87.52 367	96.42 224	85.76 269	94.72 208	93.89 310	82.73 279	98.16 234	90.93 166	98.55 187	98.04 181

UnsupCasMVSNet_bld		88.50 307	88.03 310	89.90 319	95.52 284	78.88 315	87.39 368	94.02 302	79.32 355	93.06 263	94.02 304	80.72 300	94.27 398	75.16 387	93.08 399	96.54 285

lupinMVS		88.34 311	87.31 319	91.45 266	94.74 309	80.06 285	87.23 369	92.27 337	71.10 411	88.83 356	91.15 368	77.02 335	98.53 195	86.67 267	96.75 308	95.76 326

pmmvs4		88.95 298	87.70 315	92.70 217	94.30 322	85.60 195	87.22 370	92.16 340	74.62 388	89.75 346	94.19 297	77.97 324	96.41 353	82.71 314	96.36 318	96.09 310

WTY-MVS		86.93 342	86.50 342	88.24 351	94.96 298	74.64 366	87.19 371	92.07 343	78.29 363	88.32 370	91.59 364	78.06 323	94.27 398	74.88 388	93.15 396	95.80 324

ET-MVSNet_ETH3D		86.15 347	84.27 358	91.79 252	93.04 349	81.28 268	87.17 372	86.14 394	79.57 349	83.65 411	88.66 398	57.10 418	98.18 232	87.74 250	95.40 342	95.90 321

MVS-HIRNet		78.83 406	80.60 391	73.51 425	93.07 347	47.37 449	87.10 373	78.00 439	68.94 423	77.53 437	97.26 122	71.45 363	94.62 391	63.28 432	88.74 425	78.55 440

xiu_mvs_v2_base		89.00 296	89.19 280	88.46 348	94.86 302	74.63 367	86.97 374	95.60 253	80.88 337	87.83 377	88.62 400	91.04 159	98.81 147	82.51 319	94.38 368	91.93 412

DPM-MVS		89.35 286	88.40 296	92.18 242	96.13 242	84.20 217	86.96 375	96.15 238	75.40 383	87.36 384	91.55 365	83.30 270	98.01 253	82.17 324	96.62 312	94.32 374

eth_miper_zixun_eth		90.72 245	90.61 254	91.05 282	92.04 376	76.84 346	86.91 376	96.67 208	85.21 282	94.41 213	93.92 308	79.53 309	98.26 225	89.76 203	97.02 295	98.06 177

dp		79.28 404	78.62 404	81.24 416	85.97 438	56.45 442	86.91 376	85.26 409	72.97 401	81.45 430	89.17 397	56.01 422	95.45 378	73.19 400	76.68 441	91.82 415

sss		87.23 333	86.82 332	88.46 348	93.96 331	77.94 327	86.84 378	92.78 326	77.59 367	87.61 382	91.83 359	78.75 315	91.92 414	77.84 365	94.20 374	95.52 339

miper_ehance_all_eth		90.48 252	90.42 259	90.69 297	91.62 388	76.57 350	86.83 379	96.18 236	83.38 305	94.06 224	92.66 343	82.20 285	98.04 248	89.79 202	97.02 295	97.45 243

CLD-MVS		91.82 223	91.41 233	93.04 199	96.37 213	83.65 225	86.82 380	97.29 160	84.65 294	92.27 297	89.67 389	92.20 129	97.85 272	83.95 305	99.47 45	97.62 231
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
cl____		90.65 248	90.56 256	90.91 290	91.85 381	76.98 344	86.75 381	95.36 268	85.53 276	94.06 224	94.89 269	77.36 332	97.98 258	90.27 187	98.98 123	97.76 221

DIV-MVS_self_test		90.65 248	90.56 256	90.91 290	91.85 381	76.99 343	86.75 381	95.36 268	85.52 278	94.06 224	94.89 269	77.37 331	97.99 257	90.28 186	98.97 128	97.76 221

PS-MVSNAJ		88.86 300	88.99 286	88.48 347	94.88 300	74.71 365	86.69 383	95.60 253	80.88 337	87.83 377	87.37 411	90.77 164	98.82 142	82.52 318	94.37 369	91.93 412

PVSNet_Blended		88.74 303	88.16 309	90.46 304	94.81 304	78.80 319	86.64 384	96.93 186	74.67 387	88.68 365	89.18 396	86.27 244	98.15 236	80.27 341	96.00 325	94.44 371

MSDG		90.82 242	90.67 253	91.26 275	94.16 324	83.08 237	86.63 385	96.19 235	90.60 164	91.94 304	91.89 358	89.16 194	95.75 371	80.96 338	94.51 366	94.95 355

cl22		89.02 293	88.50 294	90.59 300	89.76 412	76.45 351	86.62 386	94.03 300	82.98 315	92.65 278	92.49 344	72.05 360	97.53 296	88.93 225	97.02 295	97.78 219

CL-MVSNet_self_test		90.04 274	89.90 270	90.47 302	95.24 294	77.81 331	86.60 387	92.62 330	85.64 272	93.25 255	93.92 308	83.84 266	96.06 364	79.93 349	98.03 244	97.53 239

PCF-MVS	84.52 17	89.12 290	87.71 314	93.34 190	96.06 247	85.84 189	86.58 388	97.31 157	68.46 425	93.61 238	93.89 310	87.51 221	98.52 196	67.85 422	98.11 236	95.66 332
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_f		86.65 345	87.13 326	85.19 392	90.28 408	86.11 180	86.52 389	91.66 350	69.76 420	95.73 153	97.21 130	69.51 370	81.28 442	89.15 221	94.40 367	88.17 428

UWE-MVS		80.29 399	79.10 400	83.87 404	91.97 379	59.56 438	86.50 390	77.43 441	75.40 383	87.79 379	88.10 405	44.08 441	96.90 336	64.23 429	96.36 318	95.14 347

testing91		83.56 371	82.45 375	86.91 371	92.92 353	67.29 410	86.33 391	88.07 379	86.22 257	84.26 406	85.76 420	48.15 431	97.17 320	76.27 380	94.08 380	96.27 302

testing222		80.54 397	78.53 405	86.58 375	92.54 362	68.60 407	86.24 392	82.72 422	83.78 304	82.68 421	84.24 429	39.25 449	95.94 368	60.25 435	95.09 352	95.20 343

Patchmatch-RL test		88.81 301	88.52 293	89.69 324	95.33 293	79.94 290	86.22 393	92.71 327	78.46 362	95.80 146	94.18 298	66.25 386	95.33 382	89.22 219	98.53 190	93.78 385

ETVMVS		79.85 402	77.94 409	85.59 386	92.97 351	66.20 419	86.13 394	80.99 430	81.41 331	83.52 414	83.89 430	41.81 447	94.98 390	56.47 439	94.25 373	95.61 336

testing99		82.94 376	81.72 379	86.59 374	92.55 360	66.53 416	86.08 395	85.70 399	85.47 279	83.95 409	85.70 421	45.87 435	97.07 327	76.58 377	93.56 387	96.17 309

Syy-MVS		84.81 357	84.93 351	84.42 399	91.71 385	63.36 432	85.89 396	81.49 426	81.03 334	85.13 397	81.64 436	77.44 328	95.00 387	85.94 280	94.12 377	94.91 358

myMVS_eth3d		79.62 403	78.26 406	83.72 405	91.71 385	61.25 436	85.89 396	81.49 426	81.03 334	85.13 397	81.64 436	32.12 450	95.00 387	71.17 414	94.12 377	94.91 358

testing11		81.98 385	80.52 392	86.38 380	92.69 357	67.13 411	85.79 398	84.80 412	82.16 325	81.19 431	85.41 423	45.24 437	96.88 337	74.14 394	93.24 393	95.14 347

FPMVS		84.50 361	83.28 368	88.16 353	96.32 222	94.49 20	85.76 399	85.47 405	83.09 312	85.20 396	94.26 294	63.79 401	86.58 437	63.72 431	91.88 413	83.40 435

IB-MVS	77.21 19	83.11 373	81.05 385	89.29 330	91.15 394	75.85 358	85.66 400	86.00 396	79.70 347	82.02 426	86.61 414	48.26 429	98.39 209	77.84 365	92.22 408	93.63 390
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
MDA-MVSNet-bldmvs		91.04 240	90.88 245	91.55 263	94.68 313	80.16 280	85.49 401	92.14 341	90.41 170	94.93 198	95.79 230	85.10 257	96.93 334	85.15 288	94.19 376	97.57 235

test_vis1_rt		85.58 351	84.58 354	88.60 343	87.97 427	86.76 159	85.45 402	93.59 309	66.43 429	87.64 380	89.20 395	79.33 310	85.38 439	81.59 329	89.98 422	93.66 389

new-patchmatchnet		88.97 297	90.79 250	83.50 407	94.28 323	55.83 443	85.34 403	93.56 311	86.18 260	95.47 164	95.73 236	83.10 272	96.51 349	85.40 285	98.06 241	98.16 171

miper_enhance_ethall		88.42 309	87.87 312	90.07 314	88.67 425	75.52 361	85.10 404	95.59 257	75.68 379	92.49 283	89.45 392	78.96 312	97.88 266	87.86 249	97.02 295	96.81 278

HyFIR lowres test		87.19 336	85.51 349	92.24 237	97.12 158	80.51 278	85.03 405	96.06 239	66.11 431	91.66 308	92.98 334	70.12 368	99.14 96	75.29 386	95.23 348	97.07 264

pmmvs3		80.83 394	78.96 402	86.45 377	87.23 432	77.48 336	84.87 406	82.31 423	63.83 436	85.03 399	89.50 391	49.66 428	93.10 408	73.12 401	95.10 351	88.78 427

test0.0.03 1		82.48 379	81.47 383	85.48 389	89.70 413	73.57 379	84.73 407	81.64 425	83.07 313	88.13 373	86.61 414	62.86 406	89.10 432	66.24 426	90.29 420	93.77 386

N_pmnet		88.90 299	87.25 322	93.83 167	94.40 321	93.81 39	84.73 407	87.09 387	79.36 354	93.26 253	92.43 348	79.29 311	91.68 415	77.50 370	97.22 288	96.00 314

GA-MVS		87.70 320	86.82 332	90.31 306	93.27 344	77.22 340	84.72 409	92.79 325	85.11 286	89.82 342	90.07 381	66.80 381	97.76 283	84.56 299	94.27 372	95.96 316

myMVS_eth3d28		80.97 392	80.42 393	82.62 411	93.35 342	58.25 441	84.70 410	85.62 403	86.31 254	84.04 408	85.20 425	46.00 434	94.07 401	62.93 433	95.65 335	95.53 338

ppachtmachnet_test		88.61 306	88.64 292	88.50 346	91.76 383	70.99 396	84.59 411	92.98 320	79.30 356	92.38 290	93.53 321	79.57 308	97.45 302	86.50 273	97.17 290	97.07 264

CHOSEN 1792x2688		87.19 336	85.92 347	91.00 286	97.13 156	79.41 303	84.51 412	95.60 253	64.14 435	90.07 337	94.81 273	78.26 322	97.14 323	73.34 398	95.38 344	96.46 293

thisisatest0515		84.72 359	82.99 371	89.90 319	92.96 352	75.33 363	84.36 413	83.42 418	77.37 369	88.27 371	86.65 413	53.94 424	98.72 164	82.56 317	97.40 283	95.67 331

cascas		87.02 341	86.28 344	89.25 332	91.56 390	76.45 351	84.33 414	96.78 199	71.01 412	86.89 388	85.91 419	81.35 294	96.94 332	83.09 311	95.60 336	94.35 373

new_pmnet		81.22 389	81.01 387	81.86 413	90.92 398	70.15 399	84.03 415	80.25 434	70.83 413	85.97 392	89.78 387	67.93 377	84.65 440	67.44 423	91.90 412	90.78 420

PAPM		81.91 386	80.11 397	87.31 365	93.87 334	72.32 390	84.02 416	93.22 317	69.47 422	76.13 440	89.84 383	72.15 359	97.23 315	53.27 441	89.02 424	92.37 409

UBG		80.28 400	78.94 403	84.31 401	92.86 354	61.77 433	83.87 417	83.31 420	77.33 370	82.78 420	83.72 431	47.60 433	96.06 364	65.47 428	93.48 389	95.11 350

our_test_3		87.55 326	87.59 316	87.44 364	91.76 383	70.48 397	83.83 418	90.55 363	79.79 345	92.06 303	92.17 353	78.63 318	95.63 372	84.77 296	94.73 361	96.22 305

WBMVS		84.00 366	83.48 366	85.56 387	92.71 356	61.52 434	83.82 419	89.38 368	79.56 350	90.74 323	93.20 329	48.21 430	97.28 312	75.63 385	98.10 238	97.88 205

miper_lstm_enhance		89.90 276	89.80 272	90.19 313	91.37 392	77.50 335	83.82 419	95.00 276	84.84 292	93.05 264	94.96 267	76.53 343	95.20 385	89.96 199	98.67 176	97.86 208

test-LLR		83.58 370	83.17 369	84.79 396	89.68 414	66.86 414	83.08 421	84.52 413	83.07 313	82.85 418	84.78 427	62.86 406	93.49 405	82.85 312	94.86 357	94.03 379

TESTMET0.1,1		79.09 405	78.04 407	82.25 412	87.52 430	64.03 429	83.08 421	80.62 432	70.28 418	80.16 433	83.22 433	44.13 440	90.56 421	79.95 347	93.36 390	92.15 410

test-mter		81.21 390	80.01 398	84.79 396	89.68 414	66.86 414	83.08 421	84.52 413	73.85 394	82.85 418	84.78 427	43.66 442	93.49 405	82.85 312	94.86 357	94.03 379

SSC-MVS3.2		89.88 277	91.06 242	86.31 382	95.90 259	63.76 430	82.68 424	92.43 335	91.42 142	92.37 292	94.58 286	86.34 242	96.60 346	84.35 302	99.50 43	98.57 130

test123		9.49 416	12.01 419	1.91 431	2.87 454	1.30 456	82.38 425	1.34 456	1.36 449	2.84 450	6.56 448	2.45 454	0.97 450	2.73 449	5.56 448	3.47 446

PMMVS		83.00 375	81.11 384	88.66 342	83.81 445	86.44 170	82.24 426	85.65 400	61.75 439	82.07 424	85.64 422	79.75 307	91.59 416	75.99 382	93.09 398	87.94 429

KD-MVS_2432*1600		82.17 382	80.75 389	86.42 378	82.04 446	70.09 400	81.75 427	90.80 359	82.56 318	90.37 331	89.30 393	42.90 444	96.11 362	74.47 390	92.55 405	93.06 398

miper_refine_blended		82.17 382	80.75 389	86.42 378	82.04 446	70.09 400	81.75 427	90.80 359	82.56 318	90.37 331	89.30 393	42.90 444	96.11 362	74.47 390	92.55 405	93.06 398

mvsany_test1		83.91 368	82.93 372	86.84 373	86.18 437	85.93 186	81.11 429	75.03 443	70.80 415	88.57 367	94.63 282	83.08 273	87.38 434	80.39 339	86.57 430	87.21 430

YYNet1		88.17 313	88.24 304	87.93 356	92.21 369	73.62 378	80.75 430	88.77 370	82.51 321	94.99 196	95.11 261	82.70 280	93.70 403	83.33 308	93.83 382	96.48 291

MDA-MVSNet_test_wron		88.16 314	88.23 305	87.93 356	92.22 368	73.71 377	80.71 431	88.84 369	82.52 320	94.88 201	95.14 259	82.70 280	93.61 404	83.28 309	93.80 383	96.46 293

testmvs		9.02 417	11.42 420	1.81 432	2.77 455	1.13 457	79.44 432	1.90 455	1.18 450	2.65 451	6.80 447	1.95 455	0.87 451	2.62 450	3.45 449	3.44 447

PVSNet	76.22 20	82.89 377	82.37 376	84.48 398	93.96 331	64.38 428	78.60 433	88.61 371	71.50 408	84.43 405	86.36 417	74.27 350	94.60 392	69.87 418	93.69 385	94.46 370

dongtai		53.72 411	53.79 414	53.51 428	79.69 448	36.70 452	77.18 434	32.53 454	71.69 406	68.63 444	60.79 443	26.65 452	73.11 444	30.67 447	36.29 446	50.73 442

kuosan		43.63 413	44.25 417	41.78 429	66.04 451	34.37 453	75.56 435	32.62 453	53.25 444	50.46 447	51.18 444	25.28 453	49.13 447	13.44 448	30.41 447	41.84 444

PVSNet_0	70.34 21	74.58 409	72.96 412	79.47 419	90.63 401	66.24 418	73.26 436	83.40 419	63.67 437	78.02 436	78.35 440	72.53 356	89.59 427	56.68 438	60.05 444	82.57 438

E-PMN		80.72 395	80.86 388	80.29 418	85.11 441	68.77 406	72.96 437	81.97 424	87.76 227	83.25 417	83.01 434	62.22 409	89.17 431	77.15 373	94.31 371	82.93 436

CHOSEN 280x420		80.04 401	77.97 408	86.23 383	90.13 409	74.53 369	72.87 438	89.59 367	66.38 430	76.29 439	85.32 424	56.96 419	95.36 380	69.49 419	94.72 362	88.79 426

EMVS		80.35 398	80.28 396	80.54 417	84.73 443	69.07 405	72.54 439	80.73 431	87.80 225	81.66 428	81.73 435	62.89 405	89.84 425	75.79 384	94.65 364	82.71 437

PMMVS2		81.31 388	83.44 367	74.92 424	90.52 403	46.49 450	69.19 440	85.23 410	84.30 299	87.95 376	94.71 279	76.95 337	84.36 441	64.07 430	98.09 239	93.89 383

tmp_tt		37.97 414	44.33 416	18.88 430	11.80 453	21.54 454	63.51 441	45.66 452	4.23 447	51.34 446	50.48 445	59.08 416	22.11 449	44.50 444	68.35 443	13.00 445

MVE	59.87 23	73.86 410	72.65 413	77.47 422	87.00 435	74.35 371	61.37 442	60.93 448	67.27 427	69.69 443	86.49 416	81.24 298	72.33 445	56.45 440	83.45 435	85.74 433
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.44 412	48.94 415	54.93 426	39.68 452	12.38 455	28.59 443	90.09 364	6.82 446	41.10 448	78.41 439	54.41 423	70.69 446	50.12 442	51.26 445	81.72 439

mmdepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet_test		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

cdsmvs_eth3d_5k		23.35 415	31.13 418	0.00 433	0.00 456	0.00 458	0.00 444	95.58 259	0.00 451	0.00 452	91.15 368	93.43 94	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		7.56 418	10.09 421	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	90.77 164	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

ab-mvs-re		7.56 418	10.08 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	90.69 378	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						61.25 436								74.55 389

MSC_two_6792asdad				95.90 69	96.54 199	89.57 93		96.87 193					99.41 44	94.06 62	99.30 79	98.72 107

PC_three_1452									75.31 385	95.87 144	95.75 235	92.93 112	96.34 359	87.18 259	98.68 174	98.04 181

No_MVS				95.90 69	96.54 199	89.57 93		96.87 193					99.41 44	94.06 62	99.30 79	98.72 107

test_one_0601					98.26 75	87.14 147		98.18 55	94.25 62	96.99 82	97.36 110	95.13 49

eth-test2					0.00 456

eth-test					0.00 456

ZD-MVS					97.23 149	90.32 84		97.54 135	84.40 297	94.78 204	95.79 230	92.76 118	99.39 54	88.72 232	98.40 202

IU-MVS					98.51 53	86.66 164		96.83 196	72.74 402	95.83 145				93.00 106	99.29 82	98.64 122

test_241102_TWO								98.10 70	91.95 112	97.54 49	97.25 123	95.37 36	99.35 65	93.29 94	99.25 90	98.49 138

test_241102_ONE					98.51 53	86.97 152		98.10 70	91.85 118	97.63 44	97.03 145	96.48 13	98.95 126

test_0728_THIRD									93.26 85	97.40 60	97.35 113	94.69 67	99.34 68	93.88 66	99.42 54	98.89 84

GSMVS																94.75 364

test_part2					98.21 80	89.41 98				96.72 95

sam_mvs1												66.64 384				94.75 364

sam_mvs												66.41 385

MTGPA								97.62 125

test_post											6.07 449	65.74 389	95.84 370

patchmatchnet-post											91.71 361	66.22 387	97.59 294

gm-plane-assit					87.08 434	59.33 439			71.22 409		83.58 432		97.20 317	73.95 395

test9_res														88.16 240	98.40 202	97.83 212

agg_prior2														87.06 262	98.36 213	97.98 190

agg_prior					96.20 234	88.89 110		96.88 192		90.21 334			98.78 155

TestCases				96.00 59	98.02 94	92.17 54		98.43 25	90.48 166	95.04 193	96.74 168	92.54 122	97.86 270	85.11 291	98.98 123	97.98 190

test_prior				94.61 128	95.95 256	87.23 144		97.36 153					98.68 175			97.93 198

新几何1				93.17 197	97.16 154	87.29 142		94.43 292	67.95 426	91.29 313	94.94 268	86.97 232	98.23 227	81.06 337	97.75 263	93.98 381

旧先验1					96.20 234	84.17 218		94.82 282			95.57 245	89.57 190			97.89 257	96.32 298

原ACMM1				92.87 210	96.91 168	84.22 216		97.01 180	76.84 375	89.64 347	94.46 289	88.00 212	98.70 171	81.53 331	98.01 247	95.70 330

testdata2													98.03 249	80.24 343

segment_acmp												92.14 130

testdata				91.03 283	96.87 171	82.01 254		94.28 296	71.55 407	92.46 285	95.42 250	85.65 251	97.38 310	82.64 315	97.27 286	93.70 388

test12				94.43 141	95.95 256	86.75 160		96.24 231		89.76 345		89.79 189	98.79 151		97.95 254	97.75 223

plane_prior7					97.71 120	88.68 114

plane_prior6					97.21 152	88.23 127						86.93 233

plane_prior5								97.81 110					98.95 126	89.26 217	98.51 194	98.60 127

plane_prior4											95.59 241

plane_prior3						88.43 125			90.35 171	93.31 248

plane_prior1					97.38 141

n2								0.00 457

nn								0.00 457

door-mid								92.13 342

lessismore_v0				93.87 164	98.05 90	83.77 224		80.32 433		97.13 72	97.91 68	77.49 327	99.11 103	92.62 116	98.08 240	98.74 105

LGP-MVS_train				96.84 42	98.36 70	92.13 56		98.25 43	91.78 125	97.07 75	97.22 128	96.38 16	99.28 81	92.07 131	99.59 30	99.11 52

test11								96.65 209

door								91.26 354

HQP5-MVS						84.89 206

BP-MVS														86.55 271

HQP4-MVS										88.81 358			98.61 183			98.15 172

HQP3-MVS								97.31 157							97.73 264

HQP2-MVS												84.76 260

NP-MVS					96.82 176	87.10 148					93.40 323

ACMMP++_ref															98.82 150

ACMMP++															99.25 90

Test By Simon												90.61 170

ITE_SJBPF				95.95 63	97.34 144	93.36 44		96.55 219	91.93 114	94.82 202	95.39 254	91.99 132	97.08 326	85.53 284	97.96 253	97.41 246

DeepMVS_CX				53.83 427	70.38 450	64.56 427		48.52 451	33.01 445	65.50 445	74.21 442	56.19 421	46.64 448	38.45 446	70.07 442	50.30 443

High-resolution multi-view benchmark