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		95.70 1	96.40 1	93.61 2	98.67 1	85.39 46	95.54 5	97.36 1	96.97 1	99.04 1	99.05 1	96.61 1	95.92 15	85.07 73	99.27 1	99.54 1

FOURS1					96.08 11	87.41 18	96.19 2	95.83 4	92.95 2	96.57 2

DTE-MVSNet		89.98 50	91.91 18	84.21 192	96.51 7	57.84 431	88.93 96	92.84 115	91.92 3	96.16 3	96.23 23	86.95 56	95.99 11	79.05 154	98.57 14	98.80 6

PS-CasMVS		90.06 46	91.92 16	84.47 181	96.56 6	58.83 420	89.04 94	92.74 119	91.40 5	96.12 4	96.06 28	87.23 52	95.57 42	79.42 149	98.74 5	99.00 2

LCM-MVSNet-Re		83.48 207	85.06 155	78.75 349	85.94 328	55.75 449	80.05 328	94.27 25	76.47 149	96.09 5	94.54 72	83.31 104	89.75 279	59.95 407	94.89 195	90.75 294

PEN-MVS		90.03 48	91.88 19	84.48 180	96.57 5	58.88 417	88.95 95	93.19 94	91.62 4	96.01 6	96.16 26	87.02 55	95.60 41	78.69 158	98.72 8	98.97 3

CP-MVSNet		89.27 65	90.91 46	84.37 182	96.34 8	58.61 423	88.66 103	92.06 142	90.78 6	95.67 7	95.17 50	81.80 139	95.54 45	79.00 155	98.69 9	98.95 4

reproduce_model		92.89 4	93.18 7	92.01 12	94.20 53	88.23 12	92.87 13	94.32 22	90.25 10	95.65 8	95.74 32	87.75 45	95.72 37	89.60 4	98.27 27	92.08 251

LTVRE_ROB	86.10 1	93.04 3	93.44 3	91.82 21	93.73 68	85.72 42	96.79 1	95.51 9	88.86 15	95.63 9	96.99 12	84.81 87	93.16 153	91.10 1	97.53 81	96.58 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
WR-MVS_H		89.91 53	91.31 35	85.71 144	96.32 9	62.39 345	89.54 84	93.31 88	90.21 11	95.57 10	95.66 36	81.42 144	95.90 16	80.94 128	98.80 2	98.84 5

reproduce-ours		92.86 5	93.22 5	91.76 22	94.39 45	87.71 14	92.40 28	94.38 20	89.82 12	95.51 11	95.49 41	89.64 22	95.82 27	89.13 6	98.26 29	91.76 262

our_new_method		92.86 5	93.22 5	91.76 22	94.39 45	87.71 14	92.40 28	94.38 20	89.82 12	95.51 11	95.49 41	89.64 22	95.82 27	89.13 6	98.26 29	91.76 262

OurMVSNet-221017-0		90.01 49	89.74 59	90.83 35	93.16 86	80.37 100	91.91 41	93.11 99	81.10 90	95.32 13	97.24 9	72.94 270	94.85 76	85.07 73	97.78 58	97.26 16

anonymousdsp		89.73 56	88.88 76	92.27 7	89.82 190	86.67 24	90.51 59	90.20 214	69.87 276	95.06 14	96.14 27	84.28 92	93.07 157	87.68 23	96.34 121	97.09 20

wuyk23d		75.13 371	79.30 303	62.63 506	75.56 502	75.18 168	80.89 313	73.10 454	75.06 176	94.76 15	95.32 44	87.73 47	52.85 541	34.16 539	97.11 91	59.85 537

ACMH	76.49 14	89.34 62	91.14 37	83.96 200	92.50 103	70.36 235	89.55 82	93.84 55	81.89 82	94.70 16	95.44 43	90.69 9	88.31 319	83.33 96	98.30 26	93.20 179
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SixPastTwentyTwo		87.20 96	87.45 96	86.45 121	92.52 102	69.19 253	87.84 117	88.05 266	81.66 84	94.64 17	96.53 19	65.94 327	94.75 80	83.02 102	96.83 101	95.41 59

mvs_tets		89.78 55	89.27 66	91.30 28	93.51 72	84.79 53	89.89 73	90.63 193	70.00 275	94.55 18	96.67 16	87.94 42	93.59 135	84.27 88	95.97 140	95.52 57

lecture		92.43 8	93.50 2	89.21 65	94.43 43	79.31 111	92.69 19	95.72 7	88.48 21	94.43 19	95.73 33	91.34 4	94.68 82	90.26 3	98.44 19	93.63 156

jajsoiax		89.41 60	88.81 80	91.19 31	93.38 78	84.72 54	89.70 76	90.29 211	69.27 284	94.39 20	96.38 20	86.02 72	93.52 140	83.96 90	95.92 146	95.34 61

test_0402		88.65 74	89.58 63	85.88 139	92.55 101	72.22 205	84.01 208	89.44 236	88.63 19	94.38 21	95.77 31	86.38 67	93.59 135	79.84 140	95.21 177	91.82 260

RoMa-HiRes		85.97 122	85.47 144	87.48 100	91.66 134	89.37 4	87.18 126	83.89 348	71.47 252	94.29 22	91.35 220	75.59 220	81.39 422	76.88 193	96.92 97	91.68 267

UniMVSNet_ETH3D		89.12 68	90.72 49	84.31 189	97.00 2	64.33 314	89.67 79	88.38 257	88.84 16	94.29 22	97.57 7	90.48 14	91.26 212	72.57 276	97.65 69	97.34 15

v7n		90.13 42	90.96 44	87.65 99	91.95 122	71.06 225	89.99 69	93.05 103	86.53 34	94.29 22	96.27 22	82.69 112	94.08 110	86.25 52	97.63 70	97.82 8

test_djsdf		89.62 57	89.01 70	91.45 25	92.36 107	82.98 72	91.98 39	90.08 217	71.54 249	94.28 25	96.54 18	81.57 142	94.27 97	86.26 50	96.49 114	97.09 20

PS-MVSNAJss		88.31 78	87.90 90	89.56 59	93.31 81	77.96 128	87.94 115	91.97 145	70.73 264	94.19 26	96.67 16	76.94 203	94.57 88	83.07 100	96.28 123	96.15 37

SED-MVS		90.46 39	91.64 22	86.93 111	94.18 54	72.65 191	90.47 60	93.69 64	83.77 60	94.11 27	94.27 84	90.28 15	95.84 25	86.03 56	97.92 51	92.29 240

test_241102_ONE					94.18 54	72.65 191		93.69 64	83.62 63	94.11 27	93.78 116	90.28 15	95.50 50

DPE-MVS		90.53 38	91.08 39	88.88 70	93.38 78	78.65 118	89.15 93	94.05 42	84.68 51	93.90 29	94.11 96	88.13 38	96.30 4	84.51 86	97.81 57	91.70 266
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		91.22 25	91.92 16	89.14 67	92.97 90	78.04 125	92.84 16	94.14 37	83.33 67	93.90 29	95.73 33	88.77 28	96.41 2	87.60 26	97.98 47	92.98 195
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMH+	77.89 11	90.73 33	91.50 26	88.44 82	93.00 89	76.26 152	89.65 80	95.55 8	87.72 26	93.89 31	94.94 55	91.62 3	93.44 144	78.35 162	98.76 3	95.61 56

TestfortrainingZip a		91.12 29	92.04 14	88.36 86	94.38 47	76.05 159	92.12 33	93.73 59	85.28 43	93.85 32	94.84 58	88.66 29	95.18 66	87.89 18	97.59 77	93.84 139

ACMM	79.39 9	90.65 34	90.99 43	89.63 57	95.03 33	83.53 65	89.62 81	93.35 84	79.20 116	93.83 33	93.60 125	90.81 8	92.96 160	85.02 76	98.45 18	92.41 227
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SR-MVS-dyc-post		92.41 9	92.41 10	92.39 4	94.13 59	88.95 7	92.87 13	94.16 33	88.75 17	93.79 34	94.43 77	88.83 27	95.51 48	87.16 37	97.60 74	92.73 204

RE-MVS-def			92.61 8		94.13 59	88.95 7	92.87 13	94.16 33	88.75 17	93.79 34	94.43 77	90.64 11		87.16 37	97.60 74	92.73 204

DVP-MVS		90.06 46	91.32 34	86.29 124	94.16 57	72.56 197	90.54 57	91.01 181	83.61 64	93.75 36	94.65 66	89.76 19	95.78 33	86.42 46	97.97 48	90.55 305
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_THIRD									85.33 41	93.75 36	94.65 66	87.44 50	95.78 33	87.41 30	98.21 33	92.98 195

test0726					94.16 57	72.56 197	90.63 54	93.90 49	83.61 64	93.75 36	94.49 74	89.76 19

LPG-MVS_test		91.47 21	91.68 21	90.82 36	94.75 40	81.69 83	90.00 67	94.27 25	82.35 77	93.67 39	94.82 61	91.18 5	95.52 46	85.36 68	98.73 6	95.23 67

LGP-MVS_train				90.82 36	94.75 40	81.69 83		94.27 25	82.35 77	93.67 39	94.82 61	91.18 5	95.52 46	85.36 68	98.73 6	95.23 67

DVP-MVS++		90.07 45	91.09 38	87.00 108	91.55 141	72.64 193	96.19 2	94.10 40	85.33 41	93.49 41	94.64 69	81.12 147	95.88 17	87.41 30	95.94 144	92.48 221

test_241102_TWO								93.71 60	83.77 60	93.49 41	94.27 84	89.27 24	95.84 25	86.03 56	97.82 56	92.04 253

test_one_0601					93.85 66	73.27 183		94.11 39	86.57 33	93.47 43	94.64 69	88.42 30

MED-MVS test				88.50 80	94.38 47	76.12 156	92.12 33	93.85 53	77.53 142	93.24 44	93.18 140		95.85 23	84.99 77	97.69 66	93.54 166

MED-MVS		90.78 32	91.50 26	88.60 78	94.38 47	76.12 156	92.12 33	93.85 53	85.28 43	93.24 44	94.84 58	87.06 54	95.85 23	84.99 77	97.78 58	93.84 139

SR-MVS		92.23 10	92.34 11	91.91 16	94.89 37	87.85 13	92.51 25	93.87 52	88.20 23	93.24 44	94.02 102	90.15 17	95.67 39	86.82 42	97.34 85	92.19 246

APD-MVS_3200maxsize		92.05 12	92.24 12	91.48 24	93.02 88	85.17 48	92.47 27	95.05 14	87.65 27	93.21 47	94.39 82	90.09 18	95.08 70	86.67 44	97.60 74	94.18 121

testf1		89.30 63	89.12 67	89.84 52	88.67 225	85.64 43	90.61 55	93.17 95	86.02 37	93.12 48	95.30 45	84.94 84	89.44 285	74.12 241	96.10 134	94.45 106

APD_test2		89.30 63	89.12 67	89.84 52	88.67 225	85.64 43	90.61 55	93.17 95	86.02 37	93.12 48	95.30 45	84.94 84	89.44 285	74.12 241	96.10 134	94.45 106

Anonymous20231211		88.40 76	89.62 62	84.73 171	90.46 174	65.27 301	88.86 97	93.02 107	87.15 29	93.05 50	97.10 10	82.28 125	92.02 186	76.70 194	97.99 45	96.88 26

RoMa-SfM		83.52 205	82.69 226	86.00 135	90.77 166	89.30 5	85.98 155	81.47 384	65.77 346	92.99 51	89.25 305	69.55 302	78.65 446	72.01 280	96.45 117	90.04 320

PMatch-Up-SfM		81.93 250	80.09 290	87.42 102	89.08 210	86.10 34	81.31 299	83.35 357	67.64 318	92.96 52	90.69 253	45.71 480	85.82 382	75.20 223	94.89 195	90.35 310

MP-MVS-pluss		90.81 31	91.08 39	89.99 49	95.97 13	79.88 103	88.13 110	94.51 19	75.79 163	92.94 53	94.96 54	88.36 32	95.01 72	90.70 2	98.40 21	95.09 74
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SD-MVS		88.96 70	89.88 56	86.22 128	91.63 135	77.07 142	89.82 74	93.77 57	78.90 120	92.88 54	92.29 183	86.11 70	90.22 257	86.24 53	97.24 88	91.36 277
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
ACMP	79.16 10	90.54 37	90.60 52	90.35 44	94.36 50	80.98 92	89.16 92	94.05 42	79.03 119	92.87 55	93.74 119	90.60 12	95.21 64	82.87 104	98.76 3	94.87 80
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TDRefinement		93.52 2	93.39 4	93.88 1	95.94 14	90.26 3	95.70 4	96.46 2	90.58 8	92.86 56	96.29 21	88.16 37	94.17 107	86.07 55	98.48 17	97.22 18

SMA-MVS		90.31 40	90.48 53	89.83 54	95.31 29	79.52 110	90.98 51	93.24 92	75.37 173	92.84 57	95.28 47	85.58 79	96.09 7	87.92 17	97.76 61	93.88 137
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
test_part2					93.86 65	77.77 130				92.84 57

v10		86.54 108	87.10 102	84.84 165	88.16 246	63.28 325	86.64 141	92.20 137	75.42 172	92.81 59	94.50 73	74.05 249	94.06 111	83.88 91	96.28 123	97.17 19

dcpmvs_2		84.23 176	85.14 153	81.50 284	88.61 229	61.98 353	82.90 256	93.11 99	68.66 298	92.77 60	92.39 175	78.50 174	87.63 333	76.99 191	92.30 308	94.90 78

v8		86.22 114	86.83 111	84.36 184	87.82 254	62.35 347	86.42 145	91.33 168	76.78 148	92.73 61	94.48 75	73.41 262	93.72 126	83.10 99	95.41 169	97.01 23

nrg030		87.85 88	88.49 82	85.91 137	90.07 185	69.73 243	87.86 116	94.20 31	74.04 192	92.70 62	94.66 65	85.88 73	91.50 200	79.72 142	97.32 86	96.50 34

SteuartSystems-ACMMP		91.16 27	91.36 30	90.55 40	93.91 64	80.97 93	91.49 45	93.48 78	82.82 74	92.60 63	93.97 104	88.19 35	96.29 5	87.61 25	98.20 35	94.39 112
Skip Steuart: Steuart Systems R&D Blog.
OPM-MVS		89.80 54	89.97 55	89.27 63	94.76 39	79.86 104	86.76 138	92.78 118	78.78 122	92.51 64	93.64 124	88.13 38	93.84 122	84.83 82	97.55 78	94.10 127
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HPM-MVS_fast		92.50 7	92.54 9	92.37 5	95.93 15	85.81 41	92.99 12	94.23 28	85.21 45	92.51 64	95.13 51	90.65 10	95.34 58	88.06 15	98.15 38	95.95 45

K. test v3		85.14 145	84.73 163	86.37 122	91.13 158	69.63 245	85.45 170	76.68 427	84.06 58	92.44 66	96.99 12	62.03 355	94.65 84	80.58 134	93.24 271	94.83 89

ME-MVS		90.09 43	90.66 50	88.38 84	92.82 97	76.12 156	89.40 90	93.70 61	83.72 62	92.39 67	93.18 140	88.02 41	95.47 51	84.99 77	97.69 66	93.54 166

ACMMP		91.91 14	91.87 20	92.03 11	95.53 26	85.91 36	93.35 11	94.16 33	82.52 76	92.39 67	94.14 94	89.15 26	95.62 40	87.35 32	98.24 31	94.56 97
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
SF-MVS		90.27 41	90.80 48	88.68 77	92.86 94	77.09 141	91.19 49	95.74 5	81.38 87	92.28 69	93.80 114	86.89 57	94.64 85	85.52 67	97.51 82	94.30 117

PMatch-SfM		81.28 263	79.37 301	87.00 108	89.23 203	85.40 45	81.27 304	81.28 386	65.97 337	92.13 70	90.30 274	44.94 492	85.43 386	74.06 244	95.14 182	90.18 317

LoFTR		76.52 351	76.53 346	76.49 400	83.36 388	80.97 93	80.82 316	68.96 485	62.47 394	92.13 70	89.95 285	51.45 441	74.61 467	64.97 361	94.67 211	73.87 516

COLMAP_ROB	83.01 3	91.97 13	91.95 15	92.04 10	93.68 69	86.15 31	93.37 10	95.10 13	90.28 9	92.11 72	95.03 53	89.75 21	94.93 74	79.95 139	98.27 27	95.04 76
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
XVG-ACMP-BASELINE		89.98 50	89.84 57	90.41 42	94.91 36	84.50 57	89.49 86	93.98 44	79.68 108	92.09 73	93.89 112	83.80 97	93.10 156	82.67 108	98.04 40	93.64 155

TranMVSNet+NR-MVSNet		87.86 87	88.76 81	85.18 157	94.02 62	64.13 315	84.38 199	91.29 169	84.88 49	92.06 74	93.84 113	86.45 64	93.73 125	73.22 267	98.66 10	97.69 9

DKM		82.99 220	82.10 236	85.66 145	90.69 170	88.83 9	82.94 253	78.86 405	66.54 333	92.02 75	88.74 319	67.79 313	78.28 448	74.39 231	96.96 95	89.85 325

MTAPA		91.52 18	91.60 23	91.29 29	96.59 4	86.29 28	92.02 38	91.81 153	84.07 57	92.00 76	94.40 81	86.63 60	95.28 61	88.59 10	98.31 25	92.30 238

ACMMP_NAP		90.65 34	91.07 41	89.42 61	95.93 15	79.54 109	89.95 71	93.68 68	77.65 138	91.97 77	94.89 56	88.38 31	95.45 53	89.27 5	97.87 55	93.27 174

FC-MVSNet-test		85.93 124	87.05 104	82.58 251	92.25 111	56.44 443	85.75 162	93.09 101	77.33 143	91.94 78	94.65 66	74.78 234	93.41 146	75.11 225	98.58 13	97.88 7

test-260524					93.36 80	75.43 166		93.68 68		91.87 79		86.66 59	95.37 56	85.83 63	97.78 58

sc_t1		87.70 91	88.94 73	83.99 198	93.47 73	67.15 276	85.05 180	88.21 265	86.81 31	91.87 79	97.65 5	85.51 81	87.91 325	74.22 235	97.63 70	96.92 25

lessismore_v0				85.95 136	91.10 159	70.99 226		70.91 475		91.79 81	94.42 79	61.76 356	92.93 162	79.52 148	93.03 278	93.93 134

HPM-MVS		92.13 11	92.20 13	91.91 16	95.58 25	84.67 55	93.51 8	94.85 15	82.88 73	91.77 82	93.94 110	90.55 13	95.73 36	88.50 11	98.23 32	95.33 62
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
PGM-MVS		91.20 26	90.95 45	91.93 14	95.67 22	85.85 39	90.00 67	93.90 49	80.32 99	91.74 83	94.41 80	88.17 36	95.98 12	86.37 48	97.99 45	93.96 133

mPP-MVS		91.69 15	91.47 28	92.37 5	96.04 12	88.48 11	92.72 18	92.60 126	83.09 70	91.54 84	94.25 88	87.67 48	95.51 48	87.21 36	98.11 39	93.12 185

HFP-MVS		91.30 23	91.39 29	91.02 32	95.43 28	84.66 56	92.58 23	93.29 90	81.99 79	91.47 85	93.96 107	88.35 33	95.56 43	87.74 21	97.74 63	92.85 201

ACMMPR		91.49 19	91.35 32	91.92 15	95.74 19	85.88 38	92.58 23	93.25 91	81.99 79	91.40 86	94.17 93	87.51 49	95.87 19	87.74 21	97.76 61	93.99 130

GST-MVS		90.96 30	91.01 42	90.82 36	95.45 27	82.73 74	91.75 43	93.74 58	80.98 92	91.38 87	93.80 114	87.20 53	95.80 29	87.10 39	97.69 66	93.93 134

test_fmvsmvis_n_1920		85.22 140	85.36 149	84.81 167	85.80 331	76.13 155	85.15 178	92.32 134	61.40 411	91.33 88	90.85 247	83.76 99	86.16 370	84.31 87	93.28 269	92.15 249

ANet_high		83.17 216	85.68 140	75.65 415	81.24 421	45.26 517	79.94 330	92.91 112	83.83 59	91.33 88	96.88 15	80.25 159	85.92 374	68.89 319	95.89 149	95.76 48

ZNCC-MVS		91.26 24	91.34 33	91.01 33	95.73 20	83.05 71	92.18 32	94.22 30	80.14 102	91.29 90	93.97 104	87.93 43	95.87 19	88.65 9	97.96 50	94.12 126

casdiffmvs_mvg		86.72 103	87.51 95	84.36 184	87.09 287	65.22 302	84.16 204	94.23 28	77.89 134	91.28 91	93.66 123	84.35 91	92.71 166	80.07 136	94.87 200	95.16 72
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DKM-HiRes		83.22 214	82.10 236	86.59 117	91.79 132	88.73 10	82.92 254	77.76 413	69.00 292	91.15 92	89.69 293	63.65 347	81.20 426	76.19 205	96.70 107	89.86 324

APD-MVS		89.54 59	89.63 61	89.26 64	92.57 100	81.34 90	90.19 66	93.08 102	80.87 94	91.13 93	93.19 139	86.22 68	95.97 13	82.23 114	97.18 90	90.45 307
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
9.14			89.29 65		91.84 129		88.80 99	95.32 12	75.14 175	91.07 94	92.89 156	87.27 51	93.78 124	83.69 95	97.55 78

CP-MVS		91.67 16	91.58 24	91.96 13	95.29 30	87.62 16	93.38 9	93.36 81	83.16 69	91.06 95	94.00 103	88.26 34	95.71 38	87.28 35	98.39 22	92.55 218

FIs		85.35 139	86.27 122	82.60 250	91.86 126	57.31 436	85.10 179	93.05 103	75.83 162	91.02 96	93.97 104	73.57 257	92.91 164	73.97 246	98.02 43	97.58 12

Casviewmamba		88.12 82	88.82 79	86.03 134	89.14 206	68.35 264	86.40 146	94.70 17	79.80 105	90.92 97	93.72 121	87.83 44	93.81 123	81.09 125	95.75 157	95.92 47

UniMVSNet_NR-MVSNet		86.84 101	87.06 103	86.17 131	92.86 94	67.02 281	82.55 265	91.56 159	83.08 71	90.92 97	91.82 201	78.25 177	93.99 113	74.16 239	98.35 23	97.49 13

DU-MVS		86.80 102	86.99 107	86.21 129	93.24 84	67.02 281	83.16 246	92.21 136	81.73 83	90.92 97	91.97 192	77.20 197	93.99 113	74.16 239	98.35 23	97.61 10

tt0805		88.09 83	89.79 58	82.98 233	93.26 83	63.94 318	91.10 50	89.64 230	85.07 46	90.91 100	91.09 233	89.16 25	91.87 191	82.03 116	95.87 150	93.13 182

V42		83.47 208	83.37 207	83.75 207	83.16 396	63.33 324	81.31 299	90.23 213	69.51 281	90.91 100	90.81 249	74.16 245	92.29 180	80.06 137	90.22 382	95.62 55

tt0320-xc		86.67 105	88.41 84	81.44 287	93.45 74	60.44 385	83.96 210	88.50 252	87.26 28	90.90 102	97.90 3	85.61 78	86.40 364	70.14 303	98.01 44	97.47 14

region2R		91.44 22	91.30 36	91.87 18	95.75 18	85.90 37	92.63 22	93.30 89	81.91 81	90.88 103	94.21 89	87.75 45	95.87 19	87.60 26	97.71 64	93.83 142

APD_test1		88.40 76	87.91 89	89.88 51	89.50 196	86.65 26	89.98 70	91.91 148	84.26 55	90.87 104	93.92 111	82.18 127	89.29 289	73.75 250	94.81 205	93.70 150

tt0320		86.63 107	88.36 85	81.41 288	93.57 71	60.73 382	84.37 200	88.61 251	87.00 30	90.75 105	97.98 2	85.54 80	86.45 361	69.75 308	97.70 65	97.06 22

WR-MVS		83.56 202	84.40 181	81.06 296	93.43 77	54.88 460	78.67 361	85.02 329	81.24 88	90.74 106	91.56 211	72.85 271	91.08 223	68.00 330	98.04 40	97.23 17

v1240		84.30 172	84.51 177	83.65 211	87.65 263	61.26 368	82.85 257	91.54 160	67.94 311	90.68 107	90.65 259	71.71 289	93.64 129	82.84 105	94.78 206	96.07 40

Elysia		88.71 72	88.89 74	88.19 90	91.26 152	72.96 187	88.10 111	93.59 73	84.31 53	90.42 108	94.10 97	74.07 246	94.82 77	88.19 13	95.92 146	96.80 27

StellarMVS		88.71 72	88.89 74	88.19 90	91.26 152	72.96 187	88.10 111	93.59 73	84.31 53	90.42 108	94.10 97	74.07 246	94.82 77	88.19 13	95.92 146	96.80 27

ZD-MVS					92.22 113	80.48 97		91.85 149	71.22 257	90.38 110	92.98 150	86.06 71	96.11 6	81.99 118	96.75 105

MIMVSNet1		83.63 199	84.59 172	80.74 302	94.06 61	62.77 333	82.72 259	84.53 341	77.57 140	90.34 111	95.92 30	76.88 209	85.83 381	61.88 392	97.42 83	93.62 157

LS3D		90.60 36	90.34 54	91.38 27	89.03 213	84.23 58	93.58 6	94.68 18	90.65 7	90.33 112	93.95 109	84.50 89	95.37 56	80.87 129	95.50 168	94.53 101

KD-MVS_self_test		81.93 250	83.14 214	78.30 360	84.75 355	52.75 476	80.37 325	89.42 237	70.24 273	90.26 113	93.39 130	74.55 241	86.77 354	68.61 325	96.64 108	95.38 60

PMVS	80.48 6	90.08 44	90.66 50	88.34 87	96.71 3	92.97 1	90.31 64	89.57 233	88.51 20	90.11 114	95.12 52	90.98 7	88.92 294	77.55 181	97.07 92	83.13 450
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PC_three_1452									58.96 439	90.06 115	91.33 221	80.66 154	93.03 159	75.78 212	95.94 144	92.48 221

v1921920		84.23 176	84.37 182	83.79 205	87.64 264	61.71 359	82.91 255	91.20 175	67.94 311	90.06 115	90.34 268	72.04 284	93.59 135	82.32 112	94.91 193	96.07 40

ITE_SJBPF				90.11 48	90.72 168	84.97 50		90.30 209	81.56 85	90.02 117	91.20 229	82.40 118	90.81 236	73.58 259	94.66 212	94.56 97

XVS		91.54 17	91.36 30	92.08 8	95.64 23	86.25 29	92.64 20	93.33 85	85.07 46	89.99 118	94.03 101	86.57 61	95.80 29	87.35 32	97.62 72	94.20 118

X-MVStestdata		85.04 149	82.70 225	92.08 8	95.64 23	86.25 29	92.64 20	93.33 85	85.07 46	89.99 118	16.05 547	86.57 61	95.80 29	87.35 32	97.62 72	94.20 118

v1192		84.57 162	84.69 168	84.21 192	87.75 258	62.88 329	83.02 249	91.43 163	69.08 289	89.98 120	90.89 244	72.70 274	93.62 133	82.41 111	94.97 192	96.13 38

Anonymous20240529		86.20 115	87.13 101	83.42 220	90.19 180	64.55 309	84.55 193	90.71 190	85.85 39	89.94 121	95.24 49	82.13 128	90.40 252	69.19 315	96.40 120	95.31 63

fmvsm_s_conf0.5_n_9		87.04 97	87.02 105	87.08 106	89.67 192	75.87 161	84.60 191	89.74 225	74.40 188	89.92 122	93.41 128	80.45 156	90.63 244	86.66 45	94.37 224	94.73 94

hybridcas		86.07 119	87.02 105	83.19 228	87.76 257	62.85 331	84.53 197	93.42 79	75.52 169	89.88 123	93.31 132	86.15 69	91.68 196	77.76 178	94.89 195	95.05 75

pmmvs6		86.52 109	88.06 88	81.90 271	92.22 113	62.28 348	84.66 190	89.15 242	83.54 66	89.85 124	97.32 8	88.08 40	86.80 353	70.43 300	97.30 87	96.62 31

v144192		84.24 175	84.41 180	83.71 209	87.59 266	61.57 360	82.95 252	91.03 180	67.82 315	89.80 125	90.49 265	73.28 266	93.51 141	81.88 121	94.89 195	96.04 42

v1144		84.54 166	84.72 165	84.00 197	87.67 262	62.55 337	82.97 251	90.93 185	70.32 270	89.80 125	90.99 237	73.50 258	93.48 142	81.69 122	94.65 213	95.97 43

MatchFormer		68.98 454	69.54 444	67.33 486	76.37 497	74.77 169	79.54 335	57.73 538	46.87 512	89.77 127	86.43 370	41.98 504	65.54 521	52.83 477	94.31 227	61.67 535

DeepC-MVS	82.31 4	89.15 67	89.08 69	89.37 62	93.64 70	79.07 114	88.54 106	94.20 31	73.53 204	89.71 128	94.82 61	85.09 83	95.77 35	84.17 89	98.03 42	93.26 176
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
RPSCF		88.00 85	86.93 109	91.22 30	90.08 183	89.30 5	89.68 78	91.11 177	79.26 115	89.68 129	94.81 64	82.44 116	87.74 330	76.54 199	88.74 411	96.61 32

IU-MVS					94.18 54	72.64 193		90.82 188	56.98 456	89.67 130				85.78 64	97.92 51	93.28 173

FMVSNet1		84.55 165	85.45 146	81.85 273	90.27 178	61.05 372	86.83 135	88.27 262	78.57 126	89.66 131	95.64 37	75.43 222	90.68 241	69.09 316	95.33 172	93.82 143

DenseAffine		81.00 271	79.38 300	85.84 140	90.25 179	87.48 17	81.47 294	78.40 409	65.68 349	89.63 132	86.45 369	58.79 378	82.05 417	67.78 333	95.99 139	87.99 375

IterMVS-LS		84.73 159	84.98 157	83.96 200	87.35 275	63.66 319	83.25 240	89.88 223	76.06 153	89.62 133	92.37 179	73.40 264	92.52 171	78.16 167	94.77 208	95.69 51
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		88.60 75	89.01 70	87.36 103	91.30 149	77.50 134	87.55 119	92.97 111	87.95 25	89.62 133	92.87 157	84.56 88	93.89 119	77.65 179	96.62 109	90.70 297

UniMVSNet (Re)		86.87 99	86.98 108	86.55 119	93.11 87	68.48 263	83.80 218	92.87 113	80.37 97	89.61 135	91.81 202	77.72 185	94.18 105	75.00 226	98.53 15	96.99 24

IS-MVSNet		86.66 106	86.82 112	86.17 131	92.05 119	66.87 285	91.21 48	88.64 249	86.30 36	89.60 136	92.59 167	69.22 305	94.91 75	73.89 247	97.89 54	96.72 29

v2v482		84.09 179	84.24 186	83.62 212	87.13 282	61.40 363	82.71 260	89.71 228	72.19 239	89.55 137	91.41 217	70.70 296	93.20 151	81.02 127	93.76 247	96.25 36

Baseline_NR-MVSNet		84.00 187	85.90 132	78.29 361	91.47 146	53.44 472	82.29 276	87.00 295	79.06 118	89.55 137	95.72 35	77.20 197	86.14 371	72.30 278	98.51 16	95.28 64

ArgMatch-SfM		79.08 303	77.37 332	84.22 191	87.80 255	86.73 23	79.32 345	78.45 407	56.81 458	89.54 139	84.95 401	55.35 416	79.21 440	68.89 319	95.21 177	86.73 399

CSCG		86.26 112	86.47 115	85.60 147	90.87 164	74.26 174	87.98 114	91.85 149	80.35 98	89.54 139	88.01 333	79.09 168	92.13 182	75.51 217	95.06 187	90.41 308

ambc				82.98 233	90.55 173	64.86 305	88.20 108	89.15 242		89.40 141	93.96 107	71.67 290	91.38 208	78.83 156	96.55 111	92.71 207

DeepPCF-MVS	81.24 5	87.28 95	86.21 124	90.49 41	91.48 145	84.90 51	83.41 235	92.38 131	70.25 272	89.35 142	90.68 255	82.85 111	94.57 88	79.55 146	95.95 143	92.00 255

LuminaMVS		83.94 190	83.51 199	85.23 155	89.78 191	71.74 211	84.76 186	87.27 280	72.60 230	89.31 143	90.60 263	64.04 340	90.95 227	79.08 153	94.11 234	92.99 193

MVStest1		70.05 442	69.26 445	72.41 451	58.62 549	55.59 451	76.61 401	65.58 503	53.44 480	89.28 144	93.32 131	22.91 548	71.44 478	74.08 243	89.52 393	90.21 316

ELoFTR		73.12 403	73.47 386	72.08 453	81.84 410	77.60 133	80.51 323	66.79 499	49.99 505	89.23 145	88.83 315	47.19 463	65.24 525	61.99 389	94.85 203	73.39 517

test_fmvsmconf0.01_n		86.68 104	86.52 114	87.18 104	85.94 328	78.30 121	86.93 131	92.20 137	65.94 339	89.16 146	93.16 143	83.10 105	89.89 273	87.81 20	94.43 220	93.35 169

MSP-MVS		89.08 69	88.16 87	91.83 19	95.76 17	86.14 32	92.75 17	93.90 49	78.43 127	89.16 146	92.25 185	72.03 285	96.36 3	88.21 12	90.93 354	92.98 195
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
XVG-OURS		89.18 66	88.83 78	90.23 46	94.28 51	86.11 33	85.91 156	93.60 72	80.16 101	89.13 148	93.44 127	83.82 96	90.98 226	83.86 92	95.30 176	93.60 159

fmvsm_s_conf0.5_n_10		85.20 142	85.25 152	85.02 162	86.01 326	71.31 220	84.96 181	91.76 155	69.10 287	88.90 149	92.56 170	73.84 253	90.63 244	86.88 40	93.26 270	93.13 182

MDA-MVSNet-bldmvs		77.47 333	76.90 340	79.16 340	79.03 465	64.59 306	66.58 506	75.67 433	73.15 217	88.86 150	88.99 313	66.94 319	81.23 425	64.71 363	88.22 423	91.64 269

EG-PatchMatch MVS		84.08 180	84.11 188	83.98 199	92.22 113	72.61 196	82.20 282	87.02 292	72.63 229	88.86 150	91.02 236	78.52 173	91.11 222	73.41 261	91.09 348	88.21 368

3Dnovator+	83.92 2	89.97 52	89.66 60	90.92 34	91.27 151	81.66 87	91.25 47	94.13 38	88.89 14	88.83 152	94.26 87	77.55 189	95.86 22	84.88 80	95.87 150	95.24 66

ArgMatch-Sym		78.58 317	76.86 341	83.71 209	87.61 265	86.40 27	78.19 367	77.45 416	55.72 463	88.82 153	82.01 452	59.68 371	78.75 445	67.43 335	94.86 201	85.98 405

fmvsm_s_conf0.5_n_5		84.56 163	84.71 166	84.11 196	87.92 251	72.09 207	84.80 182	88.64 249	64.43 369	88.77 154	91.78 204	78.07 179	87.95 324	85.85 62	92.18 316	92.30 238

EI-MVSNet-UG-set		85.04 149	84.44 179	86.85 113	83.87 376	72.52 199	83.82 216	85.15 325	80.27 100	88.75 155	85.45 390	79.95 162	91.90 189	81.92 120	90.80 363	96.13 38

EI-MVSNet-Vis-set		85.12 147	84.53 176	86.88 112	84.01 372	72.76 190	83.91 214	85.18 324	80.44 95	88.75 155	85.49 388	80.08 160	91.92 188	82.02 117	90.85 359	95.97 43

BridgeMVS		84.80 155	85.40 147	83.00 232	88.95 216	61.44 362	90.42 63	92.37 133	71.48 251	88.72 157	93.13 144	70.16 300	95.15 67	79.26 152	94.11 234	92.41 227

OMC-MVS		88.19 79	87.52 94	90.19 47	91.94 124	81.68 85	87.49 122	93.17 95	76.02 155	88.64 158	91.22 227	84.24 93	93.37 147	77.97 176	97.03 93	95.52 57

RRT-MVS		82.97 221	83.44 202	81.57 281	85.06 348	58.04 429	87.20 124	90.37 203	77.88 135	88.59 159	93.70 122	63.17 349	93.05 158	76.49 200	88.47 415	93.62 157

test_fmvsmconf0.1_n		86.18 117	85.88 133	87.08 106	85.26 344	78.25 122	85.82 160	91.82 151	65.33 356	88.55 160	92.35 182	82.62 115	89.80 275	86.87 41	94.32 226	93.18 181

UA-Net		91.49 19	91.53 25	91.39 26	94.98 34	82.95 73	93.52 7	92.79 117	88.22 22	88.53 161	97.64 6	83.45 102	94.55 90	86.02 59	98.60 12	96.67 30

MP-MVS		91.14 28	90.91 46	91.83 19	96.18 10	86.88 22	92.20 31	93.03 106	82.59 75	88.52 162	94.37 83	86.74 58	95.41 55	86.32 49	98.21 33	93.19 180
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
sasdasda		85.50 129	86.14 125	83.58 214	87.97 248	67.13 277	87.55 119	94.32 22	73.44 207	88.47 163	87.54 349	86.45 64	91.06 224	75.76 213	93.76 247	92.54 219

canonicalmvs		85.50 129	86.14 125	83.58 214	87.97 248	67.13 277	87.55 119	94.32 22	73.44 207	88.47 163	87.54 349	86.45 64	91.06 224	75.76 213	93.76 247	92.54 219

NR-MVSNet		86.00 120	86.22 123	85.34 154	93.24 84	64.56 308	82.21 280	90.46 199	80.99 91	88.42 165	91.97 192	77.56 188	93.85 120	72.46 277	98.65 11	97.61 10

alignmvs		83.94 190	83.98 191	83.80 204	87.80 255	67.88 271	84.54 195	91.42 165	73.27 215	88.41 166	87.96 334	72.33 278	90.83 235	76.02 210	94.11 234	92.69 208

TransMVSNet (Re)		84.02 186	85.74 139	78.85 346	91.00 161	55.20 458	82.29 276	87.26 281	79.65 109	88.38 167	95.52 40	83.00 107	86.88 349	67.97 331	96.60 110	94.45 106

PM-MVS		80.20 291	79.00 305	83.78 206	88.17 244	86.66 25	81.31 299	66.81 498	69.64 278	88.33 168	90.19 278	64.58 334	83.63 407	71.99 281	90.03 385	81.06 478

fmvsm_s_conf0.5_n_3		86.19 116	87.27 99	82.95 235	86.91 295	70.38 234	85.31 174	92.61 125	75.59 167	88.32 169	92.87 157	82.22 126	88.63 308	88.80 8	92.82 287	89.83 326

tttt0517		81.07 269	79.58 297	85.52 149	88.99 215	66.45 290	87.03 130	75.51 435	73.76 196	88.32 169	90.20 277	37.96 513	94.16 109	79.36 151	95.13 183	95.93 46

FE-MVSNET2		82.80 224	83.51 199	80.67 307	89.08 210	58.46 424	82.40 273	89.26 238	71.25 256	88.24 171	94.07 99	75.75 218	89.56 280	65.91 350	95.67 163	93.98 131

casdiffmvs		85.21 141	85.85 134	83.31 223	86.17 320	62.77 333	83.03 248	93.93 47	74.69 181	88.21 172	92.68 166	82.29 124	91.89 190	77.87 177	93.75 250	95.27 65
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_vis3_rt		71.42 426	70.67 428	73.64 437	69.66 533	70.46 232	66.97 505	89.73 226	42.68 531	88.20 173	83.04 435	43.77 496	60.07 533	65.35 357	86.66 447	90.39 309

SSC-MVS		77.55 332	81.64 248	65.29 499	90.46 174	20.33 552	73.56 449	68.28 487	85.44 40	88.18 174	94.64 69	70.93 294	81.33 423	71.25 287	92.03 320	94.20 118

balanced_ft_v1		83.49 206	83.93 193	82.19 263	86.46 305	59.61 401	90.81 52	90.92 186	71.78 246	88.08 175	92.56 170	66.97 318	94.54 91	75.34 221	92.42 304	92.42 225

MVSMamba_PlusPlus		87.53 93	88.86 77	83.54 218	92.03 120	62.26 349	91.49 45	92.62 123	88.07 24	88.07 176	96.17 25	72.24 280	95.79 32	84.85 81	94.16 233	92.58 216

MGCFI-Net		85.04 149	85.95 130	82.31 261	87.52 268	63.59 321	86.23 150	93.96 45	73.46 205	88.07 176	87.83 344	86.46 63	90.87 234	76.17 207	93.89 242	92.47 223

v148		82.31 234	82.48 232	81.81 276	85.59 337	59.66 399	81.47 294	86.02 308	72.85 224	88.05 178	90.65 259	70.73 295	90.91 231	75.15 224	91.79 328	94.87 80

AstraMVS		81.67 255	81.40 258	82.48 256	87.06 290	66.47 289	81.41 296	81.68 380	68.78 295	88.00 179	90.95 242	65.70 329	87.86 329	76.66 195	92.38 305	93.12 185

AllTest		87.97 86	87.40 98	89.68 55	91.59 136	83.40 66	89.50 85	95.44 10	79.47 110	88.00 179	93.03 148	82.66 113	91.47 202	70.81 291	96.14 131	94.16 123

TestCases				89.68 55	91.59 136	83.40 66		95.44 10	79.47 110	88.00 179	93.03 148	82.66 113	91.47 202	70.81 291	96.14 131	94.16 123

fmvsm_s_conf0.1_n_2		83.82 193	83.49 201	84.84 165	85.99 327	70.19 237	80.93 312	87.58 276	67.26 325	87.94 182	92.37 179	71.40 292	88.01 321	86.03 56	91.87 327	96.31 35

fmvsm_s_conf0.5_n_8		85.48 131	85.75 138	84.68 174	87.10 285	69.98 239	84.28 202	92.68 120	74.77 179	87.90 183	92.36 181	73.94 250	90.41 251	85.95 61	92.74 289	93.66 151

viewdifsd2359ckpt11		82.46 232	82.98 218	80.88 299	83.53 379	61.00 375	79.46 342	85.97 310	69.48 282	87.89 184	91.31 223	82.10 129	88.61 309	74.28 233	92.86 284	93.02 189

viewmsd2359difaftdt		82.46 232	82.99 217	80.88 299	83.52 380	61.00 375	79.46 342	85.97 310	69.48 282	87.89 184	91.31 223	82.10 129	88.61 309	74.28 233	92.86 284	93.02 189

pm-mvs1		83.69 196	84.95 159	79.91 323	90.04 187	59.66 399	82.43 271	87.44 277	75.52 169	87.85 186	95.26 48	81.25 146	85.65 385	68.74 323	96.04 136	94.42 110

PCF-MVS	74.62 15	82.15 242	80.92 270	85.84 140	89.43 198	72.30 203	80.53 322	91.82 151	57.36 452	87.81 187	89.92 288	77.67 186	93.63 130	58.69 416	95.08 186	91.58 271
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.5_n_2		83.62 200	83.29 208	84.62 175	85.43 341	70.18 238	80.61 321	87.24 282	67.14 326	87.79 188	91.87 194	71.79 288	87.98 323	86.00 60	91.77 330	95.71 50

guyue		81.57 257	81.37 260	82.15 265	86.39 308	66.13 293	81.54 293	83.21 359	69.79 277	87.77 189	89.95 285	65.36 332	87.64 332	75.88 211	92.49 302	92.67 209

KinetiMVS		85.95 123	86.10 127	85.50 151	87.56 267	69.78 241	83.70 221	89.83 224	80.42 96	87.76 190	93.24 138	73.76 255	91.54 199	85.03 75	93.62 256	95.19 69

mvs5depth		83.82 193	84.54 175	81.68 279	82.23 404	68.65 261	86.89 132	89.90 222	80.02 104	87.74 191	97.86 4	64.19 339	82.02 418	76.37 201	95.63 165	94.35 113

test_fmvsmconf_n		85.88 125	85.51 143	86.99 110	84.77 354	78.21 123	85.40 172	91.39 166	65.32 357	87.72 192	91.81 202	82.33 120	89.78 276	86.68 43	94.20 231	92.99 193

FMVSNet2		81.31 262	81.61 250	80.41 313	86.38 310	58.75 421	83.93 213	86.58 299	72.43 231	87.65 193	92.98 150	63.78 344	90.22 257	66.86 337	93.92 241	92.27 242

E5new		85.44 134	86.37 117	82.66 245	88.22 241	61.86 354	83.59 225	93.70 61	73.64 199	87.62 194	93.30 133	85.85 74	91.26 212	78.02 170	93.40 261	94.86 84

E5		85.44 134	86.37 117	82.66 245	88.22 241	61.86 354	83.59 225	93.70 61	73.64 199	87.62 194	93.30 133	85.85 74	91.26 212	78.02 170	93.40 261	94.86 84

E6new		85.44 134	86.37 117	82.66 245	88.23 239	61.86 354	83.59 225	93.69 64	73.64 199	87.61 196	93.30 133	85.85 74	91.26 212	78.02 170	93.40 261	94.86 84

E6		85.44 134	86.37 117	82.66 245	88.23 239	61.86 354	83.59 225	93.69 64	73.64 199	87.61 196	93.30 133	85.85 74	91.26 212	78.02 170	93.40 261	94.86 84

viewdifsd2359ckpt07		83.41 212	84.35 183	80.56 309	85.84 330	58.93 416	79.47 340	91.28 170	73.01 221	87.59 198	92.07 188	85.24 82	88.68 305	73.59 258	91.11 346	94.09 128

GeoE		85.45 133	85.81 135	84.37 182	90.08 183	67.07 280	85.86 159	91.39 166	72.33 236	87.59 198	90.25 275	84.85 86	92.37 176	78.00 174	91.94 324	93.66 151

VPA-MVSNet		83.47 208	84.73 163	79.69 328	90.29 177	57.52 434	81.30 302	88.69 248	76.29 151	87.58 200	94.44 76	80.60 155	87.20 342	66.60 342	96.82 102	94.34 114

casdiffseed414692147		85.64 128	86.08 128	84.32 187	87.49 270	65.55 300	85.81 161	93.00 110	75.85 161	87.50 201	93.40 129	83.10 105	91.71 195	73.70 255	94.84 204	95.69 51

CPTT-MVS		89.39 61	88.98 72	90.63 39	95.09 32	86.95 20	92.09 37	92.30 135	79.74 107	87.50 201	92.38 176	81.42 144	93.28 149	83.07 100	97.24 88	91.67 268

VDDNet		84.35 170	85.39 148	81.25 290	95.13 31	59.32 405	85.42 171	81.11 387	86.41 35	87.41 203	96.21 24	73.61 256	90.61 246	66.33 344	96.85 99	93.81 146

VortexMVS		80.51 280	80.63 274	80.15 319	83.36 388	61.82 358	80.63 320	88.00 268	67.11 327	87.23 204	89.10 311	63.98 341	88.00 322	73.63 257	92.63 292	90.64 302

ALIKED-LG		78.19 324	77.07 335	81.54 282	84.95 349	86.95 20	86.16 152	83.96 347	56.64 460	87.21 205	90.05 284	51.36 442	78.05 450	57.73 426	95.60 166	79.63 490

c3_l		81.64 256	81.59 251	81.79 278	80.86 429	59.15 411	78.61 362	90.18 215	68.36 302	87.20 206	87.11 361	69.39 303	91.62 197	78.16 167	94.43 220	94.60 96

VDD-MVS		84.23 176	84.58 173	83.20 226	91.17 157	65.16 304	83.25 240	84.97 332	79.79 106	87.18 207	94.27 84	74.77 235	90.89 232	69.24 312	96.54 112	93.55 165

SIFT-NCMNet		71.70 422	70.97 425	73.90 431	77.55 481	81.03 91	71.58 472	63.31 516	63.91 378	87.12 208	81.00 463	50.00 454	64.64 528	49.37 497	94.86 201	76.04 511

MSLP-MVS++		85.00 152	86.03 129	81.90 271	91.84 129	71.56 218	86.75 139	93.02 107	75.95 158	87.12 208	89.39 299	77.98 180	89.40 288	77.46 183	94.78 206	84.75 421

baseline		85.20 142	85.93 131	83.02 231	86.30 315	62.37 346	84.55 193	93.96 45	74.48 185	87.12 208	92.03 191	82.30 122	91.94 187	78.39 160	94.21 229	94.74 93

YYNet1		70.06 441	70.44 432	68.90 474	73.76 514	53.42 473	58.99 529	67.20 494	58.42 442	87.10 211	85.39 392	59.82 369	67.32 510	59.79 408	83.50 486	85.96 406

MDA-MVSNet_test_wron		70.05 442	70.44 432	68.88 475	73.84 513	53.47 471	58.93 530	67.28 493	58.43 441	87.09 212	85.40 391	59.80 370	67.25 511	59.66 409	83.54 485	85.92 408

test_fmvs3		75.72 365	75.20 363	77.27 383	75.01 509	69.47 247	78.93 354	84.88 335	46.67 514	87.08 213	87.84 343	50.44 452	71.62 476	77.42 186	88.53 413	90.72 295

CNVR-MVS		87.81 89	87.68 92	88.21 89	92.87 92	77.30 140	85.25 175	91.23 174	77.31 144	87.07 214	91.47 216	82.94 108	94.71 81	84.67 84	96.27 125	92.62 212

EPP-MVSNet		85.47 132	85.04 156	86.77 115	91.52 144	69.37 248	91.63 44	87.98 269	81.51 86	87.05 215	91.83 200	66.18 326	95.29 59	70.75 294	96.89 98	95.64 54

TinyColmap		81.25 264	82.34 234	77.99 367	85.33 342	60.68 383	82.32 275	88.33 259	71.26 255	86.97 216	92.22 187	77.10 200	86.98 347	62.37 383	95.17 180	86.31 403

eth_miper_zixun_eth		80.84 274	80.22 284	82.71 243	81.41 419	60.98 378	77.81 375	90.14 216	67.31 324	86.95 217	87.24 358	64.26 337	92.31 178	75.23 222	91.61 335	94.85 88

E4		84.75 158	85.46 145	82.61 249	88.17 244	61.55 361	81.39 297	93.55 76	73.13 219	86.83 218	92.83 159	84.17 94	91.48 201	76.92 192	92.19 315	94.80 91

Anonymous20240521		80.18 292	81.25 262	76.95 390	83.15 397	60.84 380	82.46 268	85.99 309	68.76 296	86.78 219	93.73 120	59.13 375	77.44 452	73.71 251	97.55 78	92.56 217

Patchmatch-RL test		74.48 383	73.68 382	76.89 393	84.83 352	66.54 287	72.29 464	69.16 484	57.70 448	86.76 220	86.33 373	45.79 479	82.59 411	69.63 309	90.65 374	81.54 469

XVG-OURS-SEG-HR		89.59 58	89.37 64	90.28 45	94.47 42	85.95 35	86.84 134	93.91 48	80.07 103	86.75 221	93.26 137	93.64 2	90.93 229	84.60 85	90.75 364	93.97 132

fmvsm_l_conf0.5_n_9		83.98 188	84.46 178	82.53 254	86.11 323	70.65 230	82.45 270	89.17 241	67.72 317	86.74 222	91.49 213	79.20 166	85.86 380	84.71 83	92.60 298	91.07 283

h-mvs33		84.25 174	82.76 224	88.72 74	91.82 131	82.60 75	84.00 209	84.98 331	71.27 253	86.70 223	90.55 264	63.04 352	93.92 118	78.26 165	94.20 231	89.63 330

hse-mvs2		83.47 208	81.81 245	88.47 81	91.03 160	82.27 79	82.61 261	83.69 352	71.27 253	86.70 223	86.05 379	63.04 352	92.41 174	78.26 165	93.62 256	90.71 296

HPM-MVS++		88.93 71	88.45 83	90.38 43	94.92 35	85.85 39	89.70 76	91.27 173	78.20 130	86.69 225	92.28 184	80.36 158	95.06 71	86.17 54	96.49 114	90.22 312

TSAR-MVS + MP.		88.14 80	87.82 91	89.09 68	95.72 21	76.74 145	92.49 26	91.19 176	67.85 314	86.63 226	94.84 58	79.58 165	95.96 14	87.62 24	94.50 216	94.56 97
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SSM_0404		85.16 144	85.09 154	85.36 153	90.14 182	69.52 246	86.17 151	91.58 157	74.41 186	86.55 227	91.49 213	78.54 171	93.97 115	73.71 251	93.21 274	92.59 215

EI-MVSNet		82.61 227	82.42 233	83.20 226	83.25 393	63.66 319	83.50 232	85.07 326	76.06 153	86.55 227	85.10 396	73.41 262	90.25 254	78.15 169	90.67 371	95.68 53

HQP_MVS		87.75 90	87.43 97	88.70 76	93.45 74	76.42 149	89.45 87	93.61 70	79.44 112	86.55 227	92.95 154	74.84 232	95.22 62	80.78 131	95.83 152	94.46 104

plane_prior3						76.85 144			77.79 137	86.55 227

BH-untuned		80.96 272	80.99 268	80.84 301	88.55 232	68.23 265	80.33 326	88.46 254	72.79 227	86.55 227	86.76 365	74.72 236	91.77 194	61.79 393	88.99 406	82.52 458

MVSTER		77.09 339	75.70 356	81.25 290	75.27 506	61.08 371	77.49 384	85.07 326	60.78 425	86.55 227	88.68 320	43.14 501	90.25 254	73.69 256	90.67 371	92.42 225

旧先验2							81.73 289		56.88 457	86.54 233			84.90 392	72.81 274

IterMVS-SCA-FT		80.64 278	79.41 298	84.34 186	83.93 374	69.66 244	76.28 407	81.09 388	72.43 231	86.47 234	90.19 278	60.46 362	93.15 154	77.45 184	86.39 451	90.22 312

WB-MVS		76.06 359	80.01 292	64.19 503	89.96 189	20.58 551	72.18 466	68.19 488	83.21 68	86.46 235	93.49 126	70.19 299	78.97 442	65.96 346	90.46 380	93.02 189

test_fmvsm_n_1920		83.60 201	82.89 220	85.74 143	85.22 345	77.74 131	84.12 206	90.48 197	59.87 436	86.45 236	91.12 232	75.65 219	85.89 378	82.28 113	90.87 357	93.58 161

fmvsm_s_conf0.5_n_4		84.38 168	84.27 185	84.74 170	87.25 278	70.84 227	83.55 230	88.45 255	68.64 299	86.29 237	91.31 223	74.97 229	88.42 315	87.87 19	90.07 384	94.95 77

DIV-MVS_self_test		80.43 282	80.23 282	81.02 297	79.99 450	59.25 407	77.07 390	87.02 292	67.38 321	86.19 238	89.22 307	63.09 350	90.16 261	76.32 202	95.80 154	93.66 151

CDPH-MVS		86.17 118	85.54 142	88.05 94	92.25 111	75.45 165	83.85 215	92.01 143	65.91 341	86.19 238	91.75 206	83.77 98	94.98 73	77.43 185	96.71 106	93.73 149

cl____		80.42 283	80.23 282	81.02 297	79.99 450	59.25 407	77.07 390	87.02 292	67.37 322	86.18 240	89.21 308	63.08 351	90.16 261	76.31 203	95.80 154	93.65 154

MVS_111021_LR		84.28 173	83.76 196	85.83 142	89.23 203	83.07 70	80.99 310	83.56 354	72.71 228	86.07 241	89.07 312	81.75 141	86.19 369	77.11 189	93.36 265	88.24 367

viewmacassd2359aftdt		84.04 185	84.78 162	81.81 276	86.43 307	60.32 387	81.95 284	92.82 116	71.56 248	86.06 242	92.98 150	81.79 140	90.28 253	76.18 206	93.24 271	94.82 90

SP-DiffGlue		78.90 308	78.86 308	79.02 341	80.36 440	79.68 108	81.86 285	80.17 395	71.69 247	86.02 243	83.77 421	57.33 395	69.38 486	79.38 150	89.12 403	88.02 374

E2		84.06 181	84.61 170	82.40 259	87.49 270	61.31 365	81.03 308	93.36 81	71.83 244	86.02 243	91.87 194	82.91 109	91.37 209	75.66 215	91.33 341	94.53 101

E3		84.06 181	84.61 170	82.40 259	87.49 270	61.30 366	81.03 308	93.36 81	71.83 244	86.01 245	91.87 194	82.91 109	91.36 210	75.66 215	91.33 341	94.53 101

GBi-Net		82.02 246	82.07 238	81.85 273	86.38 310	61.05 372	86.83 135	88.27 262	72.43 231	86.00 246	95.64 37	63.78 344	90.68 241	65.95 347	93.34 266	93.82 143

test1		82.02 246	82.07 238	81.85 273	86.38 310	61.05 372	86.83 135	88.27 262	72.43 231	86.00 246	95.64 37	63.78 344	90.68 241	65.95 347	93.34 266	93.82 143

FMVSNet3		78.80 312	78.55 315	79.57 331	82.89 401	56.89 441	81.76 288	85.77 313	69.04 290	86.00 246	90.44 266	51.75 440	90.09 267	65.95 347	93.34 266	91.72 264

miper_ehance_all_eth		80.34 286	80.04 291	81.24 293	79.82 454	58.95 415	77.66 377	89.66 229	65.75 347	85.99 249	85.11 395	68.29 310	91.42 206	76.03 209	92.03 320	93.33 170

tfpnnormal		81.79 254	82.95 219	78.31 359	88.93 217	55.40 454	80.83 315	82.85 364	76.81 147	85.90 250	94.14 94	74.58 239	86.51 359	66.82 340	95.68 161	93.01 192

TAPA-MVS	77.73 12	85.71 127	84.83 161	88.37 85	88.78 224	79.72 105	87.15 128	93.50 77	69.17 285	85.80 251	89.56 295	80.76 152	92.13 182	73.21 272	95.51 167	93.25 177
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
mamba_0408		83.44 211	82.88 221	85.11 158	89.13 207	68.97 256	72.73 461	91.28 170	72.90 222	85.68 252	90.61 261	76.78 210	93.97 115	73.37 263	93.47 258	92.38 232

SSM_04072		81.44 260	82.88 221	77.10 386	89.13 207	68.97 256	72.73 461	91.28 170	72.90 222	85.68 252	90.61 261	76.78 210	69.94 484	73.37 263	93.47 258	92.38 232

SSM_0407		84.89 154	84.85 160	85.01 163	89.13 207	68.97 256	85.60 166	91.58 157	74.41 186	85.68 252	91.49 213	78.54 171	93.69 127	73.71 251	93.47 258	92.38 232

TSAR-MVS + GP.		83.95 189	82.69 226	87.72 97	89.27 202	81.45 89	83.72 220	81.58 383	74.73 180	85.66 255	86.06 378	72.56 276	92.69 168	75.44 219	95.21 177	89.01 353

EU-MVSNet		75.12 372	74.43 375	77.18 385	83.11 398	59.48 403	85.71 164	82.43 371	39.76 536	85.64 256	88.76 317	44.71 494	87.88 327	73.86 248	85.88 459	84.16 432

SIFT-ConvMatch		74.17 387	72.94 396	77.87 370	80.47 437	83.15 69	74.56 433	63.87 513	63.44 380	85.61 257	83.95 418	53.15 428	69.97 483	57.21 430	94.21 229	80.48 483

MonoMVSNet		76.66 346	77.26 334	74.86 423	79.86 453	54.34 464	86.26 149	86.08 305	71.08 259	85.59 258	88.68 320	53.95 423	85.93 373	63.86 371	80.02 506	84.32 427

LF4IMVS		82.75 226	81.93 243	85.19 156	82.08 405	80.15 102	85.53 167	88.76 246	68.01 308	85.58 259	87.75 345	71.80 287	86.85 351	74.02 245	93.87 243	88.58 360

Patchmtry		76.56 350	77.46 329	73.83 433	79.37 461	46.60 510	82.41 272	76.90 424	73.81 195	85.56 260	92.38 176	48.07 461	83.98 404	63.36 377	95.31 175	90.92 289

MVS_111021_HR		84.63 160	84.34 184	85.49 152	90.18 181	75.86 162	79.23 351	87.13 286	73.35 209	85.56 260	89.34 301	83.60 101	90.50 248	76.64 196	94.05 238	90.09 319

testdata				79.54 333	92.87 92	72.34 202		80.14 396	59.91 435	85.47 262	91.75 206	67.96 312	85.24 388	68.57 327	92.18 316	81.06 478

FE-MVSNET		78.46 319	79.36 302	75.75 412	86.53 301	54.53 462	78.03 368	85.35 320	69.01 291	85.41 263	90.68 255	64.27 336	85.73 383	62.59 382	92.35 307	87.00 394

viewcassd2359sk11		83.53 204	83.96 192	82.25 262	86.97 294	61.13 370	80.80 317	93.22 93	70.97 261	85.36 264	91.08 234	81.84 138	91.29 211	74.79 228	90.58 376	94.33 115

mvsmamba		80.30 288	78.87 307	84.58 177	88.12 247	67.55 273	92.35 30	84.88 335	63.15 384	85.33 265	90.91 243	50.71 448	95.20 65	66.36 343	87.98 425	90.99 286

SIFT-UM-Cal		73.50 397	72.76 399	75.71 414	79.21 463	81.68 85	72.85 460	68.91 486	62.93 385	85.31 266	83.39 431	52.88 430	67.56 509	54.97 455	94.42 223	77.89 505

test1111		78.53 318	78.85 310	77.56 375	92.22 113	47.49 505	82.61 261	69.24 483	72.43 231	85.28 267	94.20 90	51.91 437	90.07 269	65.36 356	96.45 117	95.11 73

thisisatest0530		79.07 304	77.33 333	84.26 190	87.13 282	64.58 307	83.66 223	75.95 430	68.86 294	85.22 268	87.36 355	38.10 510	93.57 138	75.47 218	94.28 228	94.62 95

XFeat-MNN		64.44 482	63.82 482	66.28 492	61.83 548	67.23 274	61.52 522	63.95 512	44.72 522	85.19 269	74.40 520	36.05 517	66.04 519	55.58 445	91.14 345	65.57 530

BP-MVS1		82.81 223	81.67 247	86.23 126	87.88 253	68.53 262	86.06 154	84.36 342	75.65 165	85.14 270	90.19 278	45.84 478	94.42 94	85.18 71	94.72 210	95.75 49

NormalMVS		86.47 110	85.32 150	89.94 50	94.43 43	80.42 98	88.63 104	93.59 73	74.56 183	85.12 271	90.34 268	66.19 324	94.20 102	76.57 197	98.44 19	95.19 69

SymmetryMVS		84.79 157	83.54 198	88.55 79	92.44 105	80.42 98	88.63 104	82.37 372	74.56 183	85.12 271	90.34 268	66.19 324	94.20 102	76.57 197	95.68 161	91.03 285

EC-MVSNet		88.01 84	88.32 86	87.09 105	89.28 201	72.03 208	90.31 64	96.31 3	80.88 93	85.12 271	89.67 294	84.47 90	95.46 52	82.56 109	96.26 126	93.77 148

dtuonlycased		77.13 338	76.99 338	77.55 378	88.60 230	57.48 435	74.18 438	81.70 379	55.62 465	85.10 274	88.40 325	74.87 230	82.26 415	56.73 434	87.66 433	92.90 200

CLD-MVS		83.18 215	82.64 228	84.79 168	89.05 212	67.82 272	77.93 373	92.52 127	68.33 303	85.07 275	81.54 459	82.06 131	92.96 160	69.35 311	97.91 53	93.57 162
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
fmvsm_s_conf0.1_n_a		82.58 229	81.93 243	84.50 178	87.68 261	73.35 180	86.14 153	77.70 414	61.64 409	85.02 276	91.62 208	77.75 183	86.24 366	82.79 106	87.07 440	93.91 136

FA-MVS(test-final)		83.13 217	83.02 216	83.43 219	86.16 322	66.08 294	88.00 113	88.36 258	75.55 168	85.02 276	92.75 164	65.12 333	92.50 172	74.94 227	91.30 343	91.72 264

viewdifsd2359ckpt09		83.64 198	83.18 212	85.03 161	87.26 277	66.99 283	85.32 173	93.83 56	65.57 351	84.99 278	89.40 298	77.30 193	93.57 138	71.16 290	93.80 245	94.54 100

DeepC-MVS_fast	80.27 8	86.23 113	85.65 141	87.96 95	91.30 149	76.92 143	87.19 125	91.99 144	70.56 265	84.96 279	90.69 253	80.01 161	95.14 68	78.37 161	95.78 156	91.82 260
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	80.37 7	84.80 155	84.71 166	85.06 160	86.36 313	74.71 170	88.77 100	90.00 219	75.65 165	84.96 279	93.17 142	74.06 248	91.19 219	78.28 164	91.09 348	89.29 340

QAPM		82.59 228	82.59 230	82.58 251	86.44 306	66.69 286	89.94 72	90.36 204	67.97 310	84.94 281	92.58 169	72.71 273	92.18 181	70.63 297	87.73 430	88.85 355

fmvsm_l_conf0.5_n_3		85.11 148	84.96 158	85.56 148	87.49 270	75.69 163	84.71 188	90.61 195	67.64 318	84.88 282	92.05 189	82.30 122	88.36 317	83.84 93	91.10 347	92.62 212

VPNet		80.25 289	81.68 246	75.94 409	92.46 104	47.98 503	76.70 397	81.67 381	73.45 206	84.87 283	92.82 160	74.66 238	86.51 359	61.66 395	96.85 99	93.33 170

NCCC		87.36 94	86.87 110	88.83 71	92.32 110	78.84 117	86.58 142	91.09 179	78.77 123	84.85 284	90.89 244	80.85 150	95.29 59	81.14 124	95.32 173	92.34 235

viewmanbaseed2359cas		82.95 222	83.43 203	81.52 283	85.18 346	60.03 392	81.36 298	92.38 131	69.55 280	84.84 285	91.38 218	79.85 164	90.09 267	74.22 235	92.09 318	94.43 109

SIFT-NCM-Cal		73.77 393	72.70 401	76.99 388	82.03 406	83.73 63	75.59 418	63.01 519	63.50 379	84.80 286	83.94 419	55.86 409	67.80 505	52.94 474	92.62 293	79.44 492

E3new		83.08 219	83.39 205	82.14 266	86.49 303	61.00 375	80.64 319	93.12 98	70.30 271	84.78 287	90.34 268	80.85 150	91.24 217	74.20 238	89.83 389	94.17 122

PHI-MVS		86.38 111	85.81 135	88.08 92	88.44 235	77.34 138	89.35 91	93.05 103	73.15 217	84.76 288	87.70 346	78.87 170	94.18 105	80.67 133	96.29 122	92.73 204

SIFT-UMatch		73.61 395	72.65 403	76.46 401	80.19 448	82.31 78	74.23 437	64.86 507	64.03 375	84.69 289	84.19 415	50.89 446	67.79 506	57.03 431	93.79 246	79.28 494

pmmvs-eth3d		78.42 323	77.04 337	82.57 253	87.44 274	74.41 173	80.86 314	79.67 398	55.68 464	84.69 289	90.31 273	60.91 360	85.42 387	62.20 385	91.59 336	87.88 380

test_prior2							83.37 236		75.43 171	84.58 291	91.57 210	81.92 136		79.54 147	96.97 94

fmvsm_s_conf0.5_n_6		84.05 183	84.14 187	83.81 203	87.75 258	71.17 223	83.42 234	91.10 178	67.90 313	84.53 292	90.70 252	73.01 269	88.73 302	85.09 72	93.72 252	91.53 274

fmvsm_s_conf0.5_n_a		82.21 238	81.51 256	84.32 187	86.56 300	73.35 180	85.46 169	77.30 420	61.81 405	84.51 293	90.88 246	77.36 191	86.21 368	82.72 107	86.97 445	93.38 168

TEST9					92.34 108	79.70 106	83.94 211	90.32 206	65.41 355	84.49 294	90.97 238	82.03 132	93.63 130

train_agg		85.98 121	85.28 151	88.07 93	92.34 108	79.70 106	83.94 211	90.32 206	65.79 343	84.49 294	90.97 238	81.93 134	93.63 130	81.21 123	96.54 112	90.88 291

fmvsm_s_conf0.1_n		82.17 240	81.59 251	83.94 202	86.87 298	71.57 217	85.19 177	77.42 418	62.27 400	84.47 296	91.33 221	76.43 213	85.91 376	83.14 97	87.14 438	94.33 115

Gipuma		84.44 167	86.33 121	78.78 348	84.20 367	73.57 178	89.55 82	90.44 200	84.24 56	84.38 297	94.89 56	76.35 216	80.40 433	76.14 208	96.80 104	82.36 460
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		64.31 484	65.85 471	59.67 517	66.54 539	62.24 351	57.76 532	70.96 474	40.13 534	84.36 298	82.09 449	46.93 464	51.67 542	61.99 389	81.89 496	65.12 531

test_8					92.09 117	78.87 116	83.82 216	90.31 208	65.79 343	84.36 298	90.96 240	81.93 134	93.44 144

SIFT-MNN		74.38 386	73.27 389	77.72 373	82.37 403	83.68 64	76.29 406	67.76 490	64.16 372	84.33 300	84.30 410	50.36 453	68.84 495	57.79 425	92.07 319	80.66 482

cl22		78.97 306	78.21 321	81.24 293	77.74 476	59.01 414	77.46 385	87.13 286	65.79 343	84.32 301	85.10 396	58.96 377	90.88 233	75.36 220	92.03 320	93.84 139

CS-MVS		88.14 80	87.67 93	89.54 60	89.56 194	79.18 113	90.47 60	94.77 16	79.37 114	84.32 301	89.33 302	83.87 95	94.53 92	82.45 110	94.89 195	94.90 78

agg_prior					91.58 139	77.69 132		90.30 209		84.32 301			93.18 152

Anonymous202405211		80.51 280	81.19 266	78.49 354	88.48 233	57.26 437	76.63 399	82.49 368	81.21 89	84.30 304	92.24 186	67.99 311	86.24 366	62.22 384	95.13 183	91.98 257

LFMVS		80.15 293	80.56 276	78.89 343	89.19 205	55.93 445	85.22 176	73.78 447	82.96 72	84.28 305	92.72 165	57.38 393	90.07 269	63.80 372	95.75 157	90.68 298

Vis-MVSNet		86.86 100	86.58 113	87.72 97	92.09 117	77.43 137	87.35 123	92.09 141	78.87 121	84.27 306	94.05 100	78.35 176	93.65 128	80.54 135	91.58 337	92.08 251
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ECVR-MVS		78.44 322	78.63 314	77.88 369	91.85 127	48.95 499	83.68 222	69.91 479	72.30 237	84.26 307	94.20 90	51.89 438	89.82 274	63.58 373	96.02 137	94.87 80

FE-MVS		79.98 297	78.86 308	83.36 221	86.47 304	66.45 290	89.73 75	84.74 339	72.80 226	84.22 308	91.38 218	44.95 491	93.60 134	63.93 370	91.50 338	90.04 320

SIFT-PointCN		72.17 416	71.14 424	75.23 419	77.93 475	79.30 112	72.22 465	64.71 509	62.60 388	84.13 309	81.00 463	46.91 465	67.69 508	55.17 452	95.64 164	78.70 500

ETV-MVS		84.31 171	83.91 195	85.52 149	88.58 231	70.40 233	84.50 198	93.37 80	78.76 124	84.07 310	78.72 487	80.39 157	95.13 69	73.82 249	92.98 280	91.04 284

SIFT-PCN-Cal		71.86 418	71.21 422	73.82 434	77.43 482	78.37 120	71.75 469	65.73 502	62.15 402	84.04 311	81.59 458	50.59 450	64.96 526	52.46 479	95.15 181	78.14 504

fmvsm_s_conf0.5_n		81.91 252	81.30 261	83.75 207	86.02 325	71.56 218	84.73 187	77.11 423	62.44 397	84.00 312	90.68 255	76.42 214	85.89 378	83.14 97	87.11 439	93.81 146

MCST-MVS		84.36 169	83.93 193	85.63 146	91.59 136	71.58 216	83.52 231	92.13 139	61.82 404	83.96 313	89.75 291	79.93 163	93.46 143	78.33 163	94.34 225	91.87 259

新几何1				82.95 235	93.96 63	78.56 119		80.24 394	55.45 467	83.93 314	91.08 234	71.19 293	88.33 318	65.84 351	93.07 277	81.95 465

mmtdpeth		85.13 146	85.78 137	83.17 229	84.65 356	74.71 170	85.87 158	90.35 205	77.94 133	83.82 315	96.96 14	77.75 183	80.03 436	78.44 159	96.21 127	94.79 92

fmvsm_l_conf0.5_n		82.06 244	81.54 255	83.60 213	83.94 373	73.90 176	83.35 237	86.10 304	58.97 438	83.80 316	90.36 267	74.23 243	86.94 348	82.90 103	90.22 382	89.94 322

GDP-MVS		82.17 240	80.85 273	86.15 133	88.65 227	68.95 259	85.65 165	93.02 107	68.42 301	83.73 317	89.54 296	45.07 490	94.31 96	79.66 144	93.87 243	95.19 69

viewdifsd2359ckpt13		82.22 237	81.98 242	82.95 235	85.48 340	64.44 311	83.17 245	92.11 140	65.97 337	83.72 318	89.73 292	77.60 187	90.80 237	70.61 298	89.42 395	93.59 160

BH-RMVSNet		80.53 279	80.22 284	81.49 285	87.19 281	66.21 292	77.79 376	86.23 302	74.21 190	83.69 319	88.50 324	73.25 267	90.75 238	63.18 379	87.90 426	87.52 386

USDC		76.63 347	76.73 344	76.34 404	83.46 383	57.20 438	80.02 329	88.04 267	52.14 491	83.65 320	91.25 226	63.24 348	86.65 356	54.66 458	94.11 234	85.17 416

miper_enhance_ethall		77.83 327	76.93 339	80.51 310	76.15 498	58.01 430	75.47 421	88.82 244	58.05 446	83.59 321	80.69 466	64.41 335	91.20 218	73.16 273	92.03 320	92.33 237

MM		87.64 92	87.15 100	89.09 68	89.51 195	76.39 151	88.68 102	86.76 296	84.54 52	83.58 322	93.78 116	73.36 265	96.48 1	87.98 16	96.21 127	94.41 111

Effi-MVS+-dtu		85.82 126	83.38 206	93.14 3	87.13 282	91.15 2	87.70 118	88.42 256	74.57 182	83.56 323	85.65 384	78.49 175	94.21 101	72.04 279	92.88 283	94.05 129

CNLPA		83.55 203	83.10 215	84.90 164	89.34 200	83.87 61	84.54 195	88.77 245	79.09 117	83.54 324	88.66 323	74.87 230	81.73 420	66.84 339	92.29 310	89.11 346

SIFT-CM-Cal		73.20 402	71.85 411	77.25 384	79.80 455	82.49 77	73.51 450	64.83 508	62.27 400	83.49 325	82.81 443	51.79 439	69.71 485	53.70 465	94.43 220	79.53 491

SDMVSNet		81.90 253	83.17 213	78.10 364	88.81 222	62.45 344	76.08 411	86.05 307	73.67 197	83.41 326	93.04 146	82.35 119	80.65 430	70.06 305	95.03 188	91.21 279

sd_testset		79.95 298	81.39 259	75.64 416	88.81 222	58.07 428	76.16 410	82.81 365	73.67 197	83.41 326	93.04 146	80.96 149	77.65 451	58.62 417	95.03 188	91.21 279

viewmamba		81.97 249	82.13 235	81.47 286	80.43 438	62.46 339	79.31 346	89.99 221	71.08 259	83.39 328	90.21 276	78.08 178	88.73 302	77.55 181	89.16 402	93.23 178

diffmvs_AUTHOR		81.24 265	81.55 254	80.30 315	80.61 434	60.22 388	77.98 372	90.48 197	67.77 316	83.34 329	89.50 297	74.69 237	87.42 337	78.78 157	90.81 362	93.27 174

OpenMVS_ROB	70.19 17	77.77 330	77.46 329	78.71 350	84.39 363	61.15 369	81.18 306	82.52 367	62.45 396	83.34 329	87.37 354	66.20 323	88.66 307	64.69 364	85.02 469	86.32 402

thres100view900		75.45 368	75.05 368	76.66 397	87.27 276	51.88 484	81.07 307	73.26 452	75.68 164	83.25 331	86.37 372	45.54 481	88.80 297	51.98 483	90.99 350	89.31 337

miper_lstm_enhance		76.45 353	76.10 352	77.51 379	76.72 491	60.97 379	64.69 512	85.04 328	63.98 377	83.20 332	88.22 329	56.67 398	78.79 444	73.22 267	93.12 276	92.78 203

IterMVS		76.91 342	76.34 350	78.64 351	80.91 426	64.03 316	76.30 405	79.03 402	64.88 365	83.11 333	89.16 309	59.90 368	84.46 397	68.61 325	85.15 467	87.42 387
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres600view7		75.97 362	75.35 362	77.85 372	87.01 291	51.84 485	80.45 324	73.26 452	75.20 174	83.10 334	86.31 375	45.54 481	89.05 291	55.03 454	92.24 312	92.66 210

mvs_anonymous		78.13 325	78.76 312	76.23 407	79.24 462	50.31 495	78.69 360	84.82 337	61.60 410	83.09 335	92.82 160	73.89 252	87.01 344	68.33 329	86.41 450	91.37 276

MASt3R-SfM		63.18 486	63.70 484	61.64 511	63.57 545	67.13 277	64.25 515	57.31 539	37.50 542	82.96 336	80.95 465	45.96 475	49.82 543	54.93 456	85.89 458	67.95 527

fmvsm_l_conf0.5_n_a		81.46 259	80.87 272	83.25 224	83.73 378	73.21 185	83.00 250	85.59 317	58.22 444	82.96 336	90.09 283	72.30 279	86.65 356	81.97 119	89.95 387	89.88 323

SP-SuperGlue		80.13 294	80.14 286	80.11 320	79.95 452	80.97 93	80.94 311	80.77 391	76.46 150	82.92 338	85.73 383	58.75 379	70.83 480	85.20 70	90.50 377	88.53 361

dtuplus		78.46 319	78.13 323	79.45 336	80.90 428	59.52 402	77.65 378	86.72 297	61.21 418	82.91 339	89.26 304	73.46 261	87.27 341	63.53 375	87.49 435	91.55 272

test_fmvs2		73.57 396	72.80 397	75.90 410	72.74 524	68.84 260	77.07 390	84.32 344	45.14 520	82.89 340	84.22 414	48.37 459	70.36 482	73.40 262	87.03 442	88.52 362

MVS_Test		82.47 231	83.22 209	80.22 317	82.62 402	57.75 433	82.54 266	91.96 146	71.16 258	82.89 340	92.52 173	77.41 190	90.50 248	80.04 138	87.84 429	92.40 229

reproduce_monomvs		74.09 389	73.23 390	76.65 399	76.52 492	54.54 461	77.50 383	81.40 385	65.85 342	82.86 342	86.67 366	27.38 541	84.53 396	70.24 302	90.66 373	90.89 290

TestfortrainingZip				84.49 179	88.84 220	70.49 231	92.12 33	91.01 181	84.70 50	82.82 343	89.25 305	74.30 242	94.06 111		90.73 369	88.92 354

test12				86.57 118	90.74 167	72.63 195		90.69 191		82.76 344		79.20 166	94.80 79		95.32 173	92.27 242

fmvsm_s_conf0.5_n_11		84.56 163	84.69 168	84.15 195	86.53 301	71.29 221	85.53 167	92.62 123	70.54 266	82.75 345	91.20 229	77.33 192	88.55 313	83.80 94	91.93 325	92.61 214

原ACMM1				84.60 176	92.81 98	74.01 175		91.50 161	62.59 389	82.73 346	90.67 258	76.53 212	94.25 99	69.24 312	95.69 160	85.55 412

test_yl		78.71 315	78.51 316	79.32 338	84.32 364	58.84 418	78.38 363	85.33 321	75.99 156	82.49 347	86.57 367	58.01 387	90.02 271	62.74 380	92.73 290	89.10 347

DCV-MVSNet		78.71 315	78.51 316	79.32 338	84.32 364	58.84 418	78.38 363	85.33 321	75.99 156	82.49 347	86.57 367	58.01 387	90.02 271	62.74 380	92.73 290	89.10 347

diffmvs		80.40 284	80.48 279	80.17 318	79.02 466	60.04 390	77.54 381	90.28 212	66.65 332	82.40 349	87.33 356	73.50 258	87.35 339	77.98 175	89.62 392	93.13 182
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmambaseed2359dif		78.80 312	78.47 318	79.78 324	80.26 446	59.28 406	77.31 387	87.13 286	60.42 429	82.37 350	88.67 322	74.58 239	87.87 328	67.78 333	87.73 430	92.19 246

test222					93.31 81	76.54 146	79.38 344	77.79 412	52.59 486	82.36 351	90.84 248	66.83 321			91.69 333	81.25 473

D2MVS		76.84 343	75.67 357	80.34 314	80.48 436	62.16 352	73.50 451	84.80 338	57.61 450	82.24 352	87.54 349	51.31 443	87.65 331	70.40 301	93.19 275	91.23 278

VNet		79.31 302	80.27 281	76.44 402	87.92 251	53.95 468	75.58 419	84.35 343	74.39 189	82.23 353	90.72 251	72.84 272	84.39 399	60.38 405	93.98 239	90.97 287

Vis-MVSNet (Re-imp)		77.82 328	77.79 327	77.92 368	88.82 221	51.29 489	83.28 238	71.97 467	74.04 192	82.23 353	89.78 290	57.38 393	89.41 287	57.22 429	95.41 169	93.05 188

API-MVS		82.28 235	82.61 229	81.30 289	86.29 316	69.79 240	88.71 101	87.67 275	78.42 128	82.15 355	84.15 417	77.98 180	91.59 198	65.39 355	92.75 288	82.51 459

icg_test_0407_2		78.46 319	79.68 295	74.78 425	85.76 332	62.46 339	68.51 493	87.91 270	65.23 358	82.12 356	87.92 338	77.27 195	72.67 471	71.67 282	90.74 365	89.20 341

IMVS_0407		81.08 268	81.23 264	80.62 308	85.76 332	62.46 339	82.46 268	87.91 270	65.23 358	82.12 356	87.92 338	77.27 195	90.18 259	71.67 282	90.74 365	89.20 341

IMVS_0403		80.93 273	81.00 267	80.72 304	85.76 332	62.46 339	81.82 287	87.91 270	65.23 358	82.07 358	87.92 338	75.91 217	90.50 248	71.67 282	90.74 365	89.20 341

DP-MVS Recon		84.05 183	83.22 209	86.52 120	91.73 133	75.27 167	83.23 243	92.40 129	72.04 241	82.04 359	88.33 328	77.91 182	93.95 117	66.17 345	95.12 185	90.34 311

onestephybrid01		81.22 266	80.90 271	82.18 264	80.05 449	64.49 310	79.47 340	89.23 239	69.10 287	81.96 360	89.27 303	75.02 227	89.12 290	73.71 251	90.24 381	92.92 199

MSDG		80.06 296	79.99 293	80.25 316	83.91 375	68.04 270	77.51 382	89.19 240	77.65 138	81.94 361	83.45 428	76.37 215	86.31 365	63.31 378	86.59 448	86.41 401

test2506		74.12 388	73.39 387	76.28 405	91.85 127	44.20 520	84.06 207	48.20 546	72.30 237	81.90 362	94.20 90	27.22 543	89.77 277	64.81 362	96.02 137	94.87 80

Fast-Effi-MVS+		81.04 270	80.57 275	82.46 257	87.50 269	63.22 326	78.37 365	89.63 231	68.01 308	81.87 363	82.08 450	82.31 121	92.65 169	67.10 336	88.30 422	91.51 275

testgi		72.36 412	74.61 371	65.59 496	80.56 435	42.82 526	68.29 494	73.35 451	66.87 330	81.84 364	89.93 287	72.08 283	66.92 513	46.05 516	92.54 300	87.01 393

tfpn200view9		74.86 378	74.23 376	76.74 396	86.24 317	52.12 481	79.24 349	73.87 445	73.34 210	81.82 365	84.60 407	46.02 472	88.80 297	51.98 483	90.99 350	89.31 337

thres400		75.14 370	74.23 376	77.86 371	86.24 317	52.12 481	79.24 349	73.87 445	73.34 210	81.82 365	84.60 407	46.02 472	88.80 297	51.98 483	90.99 350	92.66 210

CL-MVSNet_self_test		76.81 344	77.38 331	75.12 421	86.90 296	51.34 487	73.20 455	80.63 393	68.30 304	81.80 367	88.40 325	66.92 320	80.90 427	55.35 450	94.90 194	93.12 185

OpenMVS	76.72 13	81.98 248	82.00 241	81.93 270	84.42 362	68.22 266	88.50 107	89.48 234	66.92 329	81.80 367	91.86 197	72.59 275	90.16 261	71.19 289	91.25 344	87.40 388

SIFT-NN-CMatch		72.68 408	71.28 419	76.88 394	78.79 468	82.59 76	73.68 446	61.02 529	60.35 430	81.79 369	83.09 434	52.94 429	68.88 494	57.28 428	92.53 301	79.16 496

MGCNet		85.37 138	84.58 173	87.75 96	85.28 343	73.36 179	86.54 144	85.71 314	77.56 141	81.78 370	92.47 174	70.29 298	96.02 10	85.59 66	95.96 141	93.87 138

AdaColmap		83.66 197	83.69 197	83.57 216	90.05 186	72.26 204	86.29 148	90.00 219	78.19 131	81.65 371	87.16 359	83.40 103	94.24 100	61.69 394	94.76 209	84.21 431

SPE-MVS-test		87.00 98	86.43 116	88.71 75	89.46 197	77.46 135	89.42 89	95.73 6	77.87 136	81.64 372	87.25 357	82.43 117	94.53 92	77.65 179	96.46 116	94.14 125

DELS-MVS		81.44 260	81.25 262	82.03 268	84.27 366	62.87 330	76.47 404	92.49 128	70.97 261	81.64 372	83.83 420	75.03 226	92.70 167	74.29 232	92.22 314	90.51 306
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
SP-LightGlue		79.92 299	79.74 294	80.46 311	80.22 447	81.52 88	81.28 303	81.81 377	75.89 160	81.60 374	84.90 402	55.82 410	71.10 479	85.62 65	90.47 378	88.76 357

SP-MNN		77.71 331	77.85 325	77.29 382	78.48 471	75.90 160	79.14 352	79.46 399	69.61 279	81.56 375	84.60 407	54.98 420	69.02 493	81.08 126	91.72 332	86.95 395

114514_t		83.10 218	82.54 231	84.77 169	92.90 91	69.10 255	86.65 140	90.62 194	54.66 473	81.46 376	90.81 249	76.98 202	94.38 95	72.62 275	96.18 129	90.82 293

TR-MVS		76.77 345	75.79 354	79.72 327	86.10 324	65.79 297	77.14 388	83.02 362	65.20 362	81.40 377	82.10 448	66.30 322	90.73 240	55.57 446	85.27 463	82.65 453

TAMVS		78.08 326	76.36 349	83.23 225	90.62 171	72.87 189	79.08 353	80.01 397	61.72 407	81.35 378	86.92 364	63.96 343	88.78 300	50.61 489	93.01 279	88.04 373

Effi-MVS+		83.90 192	84.01 190	83.57 216	87.22 280	65.61 299	86.55 143	92.40 129	78.64 125	81.34 379	84.18 416	83.65 100	92.93 162	74.22 235	87.87 427	92.17 248

hybridnocas07		79.65 301	79.65 296	79.63 330	78.06 472	59.34 404	77.00 394	88.72 247	66.51 334	81.08 380	89.36 300	72.35 277	87.12 343	74.56 229	89.20 400	92.44 224

testing3		71.53 425	70.79 427	73.77 436	88.89 219	41.86 528	76.60 402	59.12 533	72.83 225	80.97 381	82.08 450	19.80 550	87.33 340	65.12 358	91.68 334	92.13 250

new-patchmatchnet		70.10 440	73.37 388	60.29 516	81.23 422	16.95 554	59.54 526	74.62 438	62.93 385	80.97 381	87.93 337	62.83 354	71.90 474	55.24 451	95.01 191	92.00 255

SIFT-NN-PointCN		72.35 413	71.17 423	75.90 410	77.68 478	80.93 96	73.48 452	63.14 518	60.88 423	80.94 383	82.91 440	52.54 434	67.74 507	55.98 441	92.95 282	79.05 498

PVSNet_Blended_VisFu		81.55 258	80.49 278	84.70 173	91.58 139	73.24 184	84.21 203	91.67 156	62.86 387	80.94 383	87.16 359	67.27 316	92.87 165	69.82 307	88.94 408	87.99 375

BH-w/o		76.57 348	76.07 353	78.10 364	86.88 297	65.92 296	77.63 379	86.33 300	65.69 348	80.89 385	79.95 475	68.97 308	90.74 239	53.01 473	85.25 464	77.62 507

PAPM_NR		83.23 213	83.19 211	83.33 222	90.90 163	65.98 295	88.19 109	90.78 189	78.13 132	80.87 386	87.92 338	73.49 260	92.42 173	70.07 304	88.40 416	91.60 270

ab-mvs		79.67 300	80.56 276	76.99 388	88.48 233	56.93 439	84.70 189	86.06 306	68.95 293	80.78 387	93.08 145	75.30 224	84.62 394	56.78 433	90.90 355	89.43 335

XXY-MVS		74.44 385	76.19 351	69.21 472	84.61 357	52.43 480	71.70 470	77.18 422	60.73 426	80.60 388	90.96 240	75.44 221	69.35 489	56.13 439	88.33 418	85.86 409

HQP4-MVS										80.56 389			94.61 86			93.56 163

HQP-NCC					91.19 154		84.77 183		73.30 212	80.55 390

ACMP_Plane					91.19 154		84.77 183		73.30 212	80.55 390

HQP-MVS		84.61 161	84.06 189	86.27 125	91.19 154	70.66 228	84.77 183	92.68 120	73.30 212	80.55 390	90.17 281	72.10 281	94.61 86	77.30 187	94.47 218	93.56 163

ALIKED-MNN		76.42 354	75.39 361	79.52 334	84.57 358	84.06 60	84.33 201	82.48 369	49.85 506	80.53 393	88.35 327	54.52 421	77.10 455	56.89 432	96.96 95	77.39 508

hybrid		79.06 305	78.94 306	79.40 337	77.99 474	59.05 413	77.07 390	88.49 253	64.42 370	80.52 394	88.78 316	71.45 291	86.82 352	73.23 266	88.52 414	92.34 235

test_cas_vis1_n_1920		69.20 453	69.12 446	69.43 471	73.68 515	62.82 332	70.38 484	77.21 421	46.18 517	80.46 395	78.95 484	52.03 436	65.53 522	65.77 353	77.45 520	79.95 487

AUN-MVS		81.18 267	78.78 311	88.39 83	90.93 162	82.14 80	82.51 267	83.67 353	64.69 367	80.29 396	85.91 382	51.07 445	92.38 175	76.29 204	93.63 255	90.65 301

HyFIR lowres test		75.12 372	72.66 402	82.50 255	91.44 147	65.19 303	72.47 463	87.31 279	46.79 513	80.29 396	84.30 410	52.70 433	92.10 185	51.88 487	86.73 446	90.22 312

test20.03		73.75 394	74.59 373	71.22 458	81.11 423	51.12 491	70.15 485	72.10 466	70.42 267	80.28 398	91.50 212	64.21 338	74.72 466	46.96 512	94.58 214	87.82 383

mvsany_test3		65.48 477	62.97 488	73.03 443	69.99 532	76.17 154	64.83 510	43.71 548	43.68 526	80.25 399	87.05 363	52.83 432	63.09 532	51.92 486	72.44 529	79.84 489

SIFT-NN-UMatch		72.46 410	71.25 420	76.08 408	78.57 470	81.88 82	74.36 434	61.59 527	61.99 403	80.24 400	83.46 427	51.20 444	68.08 504	57.95 424	91.91 326	78.28 503

F-COLMAP		84.97 153	83.42 204	89.63 57	92.39 106	83.40 66	88.83 98	91.92 147	73.19 216	80.18 401	89.15 310	77.04 201	93.28 149	65.82 352	92.28 311	92.21 245

GA-MVS		75.83 363	74.61 371	79.48 335	81.87 408	59.25 407	73.42 453	82.88 363	68.68 297	79.75 402	81.80 454	50.62 449	89.46 283	66.85 338	85.64 460	89.72 327

xiu_mvs_v1_base_debu		80.84 274	80.14 286	82.93 238	88.31 236	71.73 212	79.53 336	87.17 283	65.43 352	79.59 403	82.73 444	76.94 203	90.14 264	73.22 267	88.33 418	86.90 396

xiu_mvs_v1_base		80.84 274	80.14 286	82.93 238	88.31 236	71.73 212	79.53 336	87.17 283	65.43 352	79.59 403	82.73 444	76.94 203	90.14 264	73.22 267	88.33 418	86.90 396

xiu_mvs_v1_base_debi		80.84 274	80.14 286	82.93 238	88.31 236	71.73 212	79.53 336	87.17 283	65.43 352	79.59 403	82.73 444	76.94 203	90.14 264	73.22 267	88.33 418	86.90 396

test_fmvs1_n		70.94 431	70.41 434	72.53 449	73.92 512	66.93 284	75.99 412	84.21 346	43.31 528	79.40 406	79.39 480	43.47 497	68.55 498	69.05 317	84.91 472	82.10 463

blended_shiyan8		76.05 360	75.11 364	78.86 345	81.76 411	59.18 410	75.09 425	83.81 349	64.70 366	79.37 407	78.35 490	58.30 383	88.68 305	62.03 388	92.56 299	88.73 358

blended_shiyan6		76.05 360	75.11 364	78.87 344	81.74 412	59.15 411	75.08 426	83.79 350	64.69 367	79.37 407	78.37 489	58.30 383	88.69 304	61.99 389	92.61 294	88.77 356

patch_mono-2		78.89 309	79.39 299	77.41 381	84.78 353	68.11 268	75.60 416	83.11 361	60.96 422	79.36 409	89.89 289	75.18 225	72.97 470	73.32 265	92.30 308	91.15 281

UnsupCasMVSNet_eth		71.63 424	72.30 408	69.62 469	76.47 494	52.70 478	70.03 486	80.97 389	59.18 437	79.36 409	88.21 330	60.50 361	69.12 491	58.33 420	77.62 518	87.04 392

ppachtmachnet_test		74.73 382	74.00 378	76.90 392	80.71 432	56.89 441	71.53 474	78.42 408	58.24 443	79.32 411	82.92 439	57.91 390	84.26 401	65.60 354	91.36 340	89.56 332

gbinet_0.2-2-1-0.02		76.14 357	74.88 369	79.92 322	80.33 445	60.02 393	75.80 414	82.44 370	66.36 336	79.24 412	75.07 517	56.11 406	90.17 260	64.60 367	93.95 240	89.58 331

MG-MVS		80.32 287	80.94 269	78.47 355	88.18 243	52.62 479	82.29 276	85.01 330	72.01 242	79.24 412	92.54 172	69.36 304	93.36 148	70.65 296	89.19 401	89.45 333

usedtu_dtu_shiyan2		78.92 307	78.15 322	81.25 290	91.33 148	73.10 186	80.75 318	79.00 404	74.19 191	79.17 414	92.04 190	67.17 317	81.33 423	42.86 522	96.81 103	89.31 337

Fast-Effi-MVS+-dtu		82.54 230	81.41 257	85.90 138	85.60 336	76.53 148	83.07 247	89.62 232	73.02 220	79.11 415	83.51 425	80.74 153	90.24 256	68.76 322	89.29 397	90.94 288

SSC-MVS3.2		73.90 391	75.67 357	68.61 480	84.11 369	41.28 529	64.17 516	72.83 457	72.09 240	79.08 416	87.94 335	70.31 297	73.89 469	55.99 440	94.49 217	90.67 300

CDS-MVSNet		77.32 335	75.40 359	83.06 230	89.00 214	72.48 200	77.90 374	82.17 374	60.81 424	78.94 417	83.49 426	59.30 373	88.76 301	54.64 459	92.37 306	87.93 379
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
baseline1		73.26 399	73.54 384	72.43 450	84.92 351	47.79 504	79.89 331	74.00 443	65.93 340	78.81 418	86.28 376	56.36 400	81.63 421	56.63 435	79.04 513	87.87 381

SIFT-NN-NCMNet		72.70 407	71.25 420	77.06 387	81.65 415	84.07 59	75.19 423	63.15 517	61.29 415	78.74 419	83.21 432	53.60 425	69.25 490	53.99 462	90.47 378	77.86 506

ttmdpeth		71.72 421	70.67 428	74.86 423	73.08 521	55.88 446	77.41 386	69.27 482	55.86 462	78.66 420	93.77 118	38.01 512	75.39 463	60.12 406	89.87 388	93.31 172

EIA-MVS		82.19 239	81.23 264	85.10 159	87.95 250	69.17 254	83.22 244	93.33 85	70.42 267	78.58 421	79.77 478	77.29 194	94.20 102	71.51 286	88.96 407	91.93 258

thres200		72.34 414	71.55 416	74.70 427	83.48 382	51.60 486	75.02 427	73.71 448	70.14 274	78.56 422	80.57 469	46.20 470	88.20 320	46.99 511	89.29 397	84.32 427

usedtu_dtu_shiyan1		75.70 366	75.08 366	77.56 375	84.10 370	55.50 452	73.58 447	84.89 333	62.48 391	78.16 423	84.24 412	58.14 385	87.47 335	59.35 411	90.82 360	89.72 327

FE-MVSNET3		75.70 366	75.08 366	77.56 375	84.10 370	55.50 452	73.58 447	84.89 333	62.48 391	78.16 423	84.24 412	58.14 385	87.47 335	59.34 412	90.82 360	89.72 327

fmvsm_s_conf0.5_n_7		82.04 245	82.05 240	82.01 269	86.98 293	71.07 224	78.70 359	89.45 235	68.07 307	78.14 425	91.61 209	74.19 244	85.92 374	79.61 145	91.73 331	89.05 350

our_test_3		71.85 419	71.59 413	72.62 447	80.71 432	53.78 469	69.72 488	71.71 471	58.80 440	78.03 426	80.51 471	56.61 399	78.84 443	62.20 385	86.04 457	85.23 415

KD-MVS_2432*1600		66.87 465	65.81 473	70.04 463	67.50 536	47.49 505	62.56 519	79.16 400	61.21 418	77.98 427	80.61 467	25.29 546	82.48 412	53.02 471	84.92 470	80.16 485

miper_refine_blended		66.87 465	65.81 473	70.04 463	67.50 536	47.49 505	62.56 519	79.16 400	61.21 418	77.98 427	80.61 467	25.29 546	82.48 412	53.02 471	84.92 470	80.16 485

jason		77.42 334	75.75 355	82.43 258	87.10 285	69.27 249	77.99 371	81.94 376	51.47 495	77.84 429	85.07 399	60.32 364	89.00 292	70.74 295	89.27 399	89.03 351
jason: jason.
MAR-MVS		80.24 290	78.74 313	84.73 171	86.87 298	78.18 124	85.75 162	87.81 274	65.67 350	77.84 429	78.50 488	73.79 254	90.53 247	61.59 396	90.87 357	85.49 414
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
FPMVS		72.29 415	72.00 409	73.14 441	88.63 228	85.00 49	74.65 431	67.39 492	71.94 243	77.80 431	87.66 347	50.48 451	75.83 460	49.95 492	79.51 507	58.58 539

test_fmvs1		69.57 448	69.05 448	71.14 460	69.15 535	65.77 298	73.98 442	83.32 358	42.83 530	77.77 432	78.27 492	43.39 500	68.50 499	68.39 328	84.38 479	79.15 497

pmmvs4		74.92 377	72.98 395	80.73 303	84.95 349	71.71 215	76.23 408	77.59 415	52.83 485	77.73 433	86.38 371	56.35 401	84.97 391	57.72 427	87.05 441	85.51 413

wanda-best-256-512		74.97 375	73.85 379	78.35 357	80.36 440	58.13 425	73.10 457	83.53 355	64.04 374	77.62 434	75.71 511	56.22 403	88.60 311	61.42 397	92.61 294	88.32 364

FE-blended-shiyan7		74.97 375	73.85 379	78.35 357	80.36 440	58.13 425	73.10 457	83.53 355	64.03 375	77.62 434	75.71 511	56.22 403	88.60 311	61.42 397	92.61 294	88.32 364

usedtu_blend_shiyan5		77.07 340	76.43 348	78.99 342	80.36 440	59.77 397	83.25 240	88.32 260	74.91 177	77.62 434	75.71 511	56.22 403	88.89 295	58.91 414	92.61 294	88.32 364

ET-MVSNet_ETH3D		75.28 369	72.77 398	82.81 242	83.03 399	68.11 268	77.09 389	76.51 428	60.67 427	77.60 437	80.52 470	38.04 511	91.15 221	70.78 293	90.68 370	89.17 345

testing3-2		70.72 435	70.97 425	69.95 465	88.93 217	34.80 542	69.85 487	66.59 500	78.42 128	77.58 438	85.55 385	31.83 527	82.08 416	46.28 513	93.73 251	92.98 195

UnsupCasMVSNet_bld		69.21 452	69.68 441	67.82 483	79.42 459	51.15 490	67.82 498	75.79 431	54.15 476	77.47 439	85.36 394	59.26 374	70.64 481	48.46 503	79.35 509	81.66 467

blend_shiyan4		70.82 433	68.15 458	78.83 347	81.06 424	59.77 397	74.58 432	83.79 350	64.94 364	77.34 440	75.47 515	29.39 534	88.89 295	58.91 414	67.86 539	87.84 382

XFeat-NN		59.92 500	59.04 502	62.58 507	63.37 546	64.42 312	55.18 534	60.26 532	41.73 532	77.26 441	69.20 529	31.98 526	58.40 538	48.23 506	84.12 481	64.93 532

WBMVS		68.76 456	68.43 455	69.75 468	83.29 391	40.30 532	67.36 501	72.21 464	57.09 455	77.05 442	85.53 387	33.68 521	80.51 431	48.79 501	90.90 355	88.45 363

Anonymous20231206		71.38 427	71.88 410	69.88 466	86.31 314	54.37 463	70.39 483	74.62 438	52.57 487	76.73 443	88.76 317	59.94 367	72.06 473	44.35 520	93.23 273	83.23 448

CMPMVS	59.41 20	75.12 372	73.57 383	79.77 325	75.84 501	67.22 275	81.21 305	82.18 373	50.78 500	76.50 444	87.66 347	55.20 417	82.99 410	62.17 387	90.64 375	89.09 349
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		72.10 417	71.69 412	73.32 438	81.57 417	53.02 475	76.77 396	78.37 410	63.31 381	76.37 445	91.85 198	36.68 515	78.98 441	47.87 507	92.45 303	87.95 377

CVMVSNet		72.62 409	71.41 417	76.28 405	83.25 393	60.34 386	83.50 232	79.02 403	37.77 541	76.33 446	85.10 396	49.60 457	87.41 338	70.54 299	77.54 519	81.08 476

PLC	73.85 16	82.09 243	80.31 280	87.45 101	90.86 165	80.29 101	85.88 157	90.65 192	68.17 306	76.32 447	86.33 373	73.12 268	92.61 170	61.40 399	90.02 386	89.44 334
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSFormer		82.23 236	81.57 253	84.19 194	85.54 338	69.26 250	91.98 39	90.08 217	71.54 249	76.23 448	85.07 399	58.69 380	94.27 97	86.26 50	88.77 409	89.03 351

lupinMVS		76.37 355	74.46 374	82.09 267	85.54 338	69.26 250	76.79 395	80.77 391	50.68 502	76.23 448	82.82 441	58.69 380	88.94 293	69.85 306	88.77 409	88.07 370

UWE-MVS		66.43 470	65.56 476	69.05 473	84.15 368	40.98 530	73.06 459	64.71 509	54.84 471	76.18 450	79.62 479	29.21 536	80.50 432	38.54 533	89.75 390	85.66 411

PatchMatch-RL		74.48 383	73.22 391	78.27 362	87.70 260	85.26 47	75.92 413	70.09 477	64.34 371	76.09 451	81.25 461	65.87 328	78.07 449	53.86 463	83.82 483	71.48 521

thisisatest0515		73.00 405	70.52 431	80.46 311	81.45 418	59.90 395	73.16 456	74.31 442	57.86 447	76.08 452	77.78 494	37.60 514	92.12 184	65.00 359	91.45 339	89.35 336

SP-NN		76.57 348	76.54 345	76.66 397	77.40 483	75.50 164	78.02 369	78.77 406	68.60 300	75.98 453	83.71 423	55.56 413	66.71 514	82.06 115	88.74 411	87.76 384

SIFT-NN		71.05 430	69.58 442	75.45 418	80.35 444	81.93 81	74.31 435	63.57 515	61.17 421	75.98 453	81.67 457	46.63 468	65.25 524	53.44 469	89.09 404	79.18 495

MS-PatchMatch		70.93 432	70.22 435	73.06 442	81.85 409	62.50 338	73.82 445	77.90 411	52.44 488	75.92 455	81.27 460	55.67 412	81.75 419	55.37 449	77.70 517	74.94 514

CHOSEN 1792x2688		72.45 411	70.56 430	78.13 363	90.02 188	63.08 327	68.72 492	83.16 360	42.99 529	75.92 455	85.46 389	57.22 396	85.18 390	49.87 494	81.67 497	86.14 404

CR-MVSNet		74.00 390	73.04 394	76.85 395	79.58 456	62.64 335	82.58 263	76.90 424	50.50 503	75.72 457	92.38 176	48.07 461	84.07 403	68.72 324	82.91 490	83.85 436

RPMNet		78.88 310	78.28 320	80.68 306	79.58 456	62.64 335	82.58 263	94.16 33	74.80 178	75.72 457	92.59 167	48.69 458	95.56 43	73.48 260	82.91 490	83.85 436

DPM-MVS		80.10 295	79.18 304	82.88 241	90.71 169	69.74 242	78.87 357	90.84 187	60.29 432	75.64 459	85.92 381	67.28 315	93.11 155	71.24 288	91.79 328	85.77 410

test_vis1_n		70.29 437	69.99 439	71.20 459	75.97 500	66.50 288	76.69 398	80.81 390	44.22 524	75.43 460	77.23 501	50.00 454	68.59 497	66.71 341	82.85 492	78.52 502

PVSNet_BlendedMVS		78.80 312	77.84 326	81.65 280	84.43 360	63.41 322	79.49 339	90.44 200	61.70 408	75.43 460	87.07 362	69.11 306	91.44 204	60.68 403	92.24 312	90.11 318

PVSNet_Blended		76.49 352	75.40 359	79.76 326	84.43 360	63.41 322	75.14 424	90.44 200	57.36 452	75.43 460	78.30 491	69.11 306	91.44 204	60.68 403	87.70 432	84.42 426

PAPR		78.84 311	78.10 324	81.07 295	85.17 347	60.22 388	82.21 280	90.57 196	62.51 390	75.32 463	84.61 406	74.99 228	92.30 179	59.48 410	88.04 424	90.68 298

N_pmnet		70.20 438	68.80 453	74.38 428	80.91 426	84.81 52	59.12 528	76.45 429	55.06 469	75.31 464	82.36 447	55.74 411	54.82 540	47.02 510	87.24 437	83.52 441

cascas		76.29 356	74.81 370	80.72 304	84.47 359	62.94 328	73.89 444	87.34 278	55.94 461	75.16 465	76.53 507	63.97 342	91.16 220	65.00 359	90.97 353	88.06 372

SD_0403		76.08 358	76.77 342	73.98 430	87.08 289	49.45 498	83.62 224	84.68 340	63.31 381	75.13 466	87.47 352	71.85 286	84.56 395	49.97 491	87.86 428	87.94 378

SCA		73.32 398	72.57 405	75.58 417	81.62 416	55.86 447	78.89 356	71.37 472	61.73 406	74.93 467	83.42 429	60.46 362	87.01 344	58.11 422	82.63 495	83.88 433

test_vis1_n_1920		71.30 428	71.58 415	70.47 461	77.58 480	59.99 394	74.25 436	84.22 345	51.06 497	74.85 468	79.10 482	55.10 418	68.83 496	68.86 321	79.20 512	82.58 455

xiu_mvs_v2_base		77.19 337	76.75 343	78.52 353	87.01 291	61.30 366	75.55 420	87.12 290	61.24 417	74.45 469	78.79 486	77.20 197	90.93 229	64.62 366	84.80 476	83.32 446

CANet		83.79 195	82.85 223	86.63 116	86.17 320	72.21 206	83.76 219	91.43 163	77.24 145	74.39 470	87.45 353	75.36 223	95.42 54	77.03 190	92.83 286	92.25 244

PS-MVSNAJ		77.04 341	76.53 346	78.56 352	87.09 287	61.40 363	75.26 422	87.13 286	61.25 416	74.38 471	77.22 502	76.94 203	90.94 228	64.63 365	84.83 475	83.35 445

ALIKED-NN		74.80 380	73.22 391	79.55 332	82.93 400	83.79 62	81.84 286	82.56 366	47.43 511	74.33 472	88.03 332	53.21 427	76.31 457	54.08 461	94.57 215	78.54 501

MVP-Stereo		75.81 364	73.51 385	82.71 243	89.35 199	73.62 177	80.06 327	85.20 323	60.30 431	73.96 473	87.94 335	57.89 391	89.45 284	52.02 482	74.87 524	85.06 418
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WB-MVSnew		68.72 457	69.01 449	67.85 482	83.22 395	43.98 521	74.93 428	65.98 501	55.09 468	73.83 474	79.11 481	65.63 330	71.89 475	38.21 534	85.04 468	87.69 385

UGNet		82.78 225	81.64 248	86.21 129	86.20 319	76.24 153	86.86 133	85.68 315	77.07 146	73.76 475	92.82 160	69.64 301	91.82 193	69.04 318	93.69 253	90.56 304
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
1112_ss		74.82 379	73.74 381	78.04 366	89.57 193	60.04 390	76.49 403	87.09 291	54.31 474	73.66 476	79.80 476	60.25 365	86.76 355	58.37 418	84.15 480	87.32 389

Test_1112_low_res		73.90 391	73.08 393	76.35 403	90.35 176	55.95 444	73.40 454	86.17 303	50.70 501	73.14 477	85.94 380	58.31 382	85.90 377	56.51 436	83.22 487	87.20 391

1314		73.22 400	72.56 406	75.20 420	80.41 439	57.84 431	81.64 291	85.36 319	51.68 494	73.10 478	76.65 506	61.45 357	85.19 389	63.54 374	79.21 511	82.59 454

test_vis1_rt		65.64 476	64.09 480	70.31 462	66.09 540	70.20 236	61.16 523	81.60 382	38.65 538	72.87 479	69.66 528	52.84 431	60.04 534	56.16 438	77.77 516	80.68 480

Patchmatch-test		65.91 473	67.38 461	61.48 513	75.51 503	43.21 525	68.84 491	63.79 514	62.48 391	72.80 480	83.42 429	44.89 493	59.52 535	48.27 505	86.45 449	81.70 466

PatchmatchNet		69.71 447	68.83 452	72.33 452	77.66 479	53.60 470	79.29 347	69.99 478	57.66 449	72.53 481	82.93 438	46.45 469	80.08 435	60.91 402	72.09 530	83.31 447
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm		67.95 459	68.08 460	67.55 484	78.74 469	43.53 523	75.60 416	67.10 497	54.92 470	72.23 482	88.10 331	42.87 502	75.97 459	52.21 480	80.95 505	83.15 449

IMVS_0404		77.24 336	77.75 328	75.73 413	85.76 332	62.46 339	70.84 479	87.91 270	65.23 358	72.21 483	87.92 338	67.48 314	75.53 462	71.67 282	90.74 365	89.20 341

pmmvs5		70.73 434	70.07 436	72.72 445	77.03 488	52.73 477	74.14 439	75.65 434	50.36 504	72.17 484	85.37 393	55.42 415	80.67 429	52.86 475	87.59 434	84.77 420

PatchT		70.52 436	72.76 399	63.79 505	79.38 460	33.53 543	77.63 379	65.37 505	73.61 203	71.77 485	92.79 163	44.38 495	75.65 461	64.53 368	85.37 462	82.18 462

MVS		73.21 401	72.59 404	75.06 422	80.97 425	60.81 381	81.64 291	85.92 312	46.03 518	71.68 486	77.54 497	68.47 309	89.77 277	55.70 444	85.39 461	74.60 515

MIMVSNet		71.09 429	71.59 413	69.57 470	87.23 279	50.07 496	78.91 355	71.83 468	60.20 434	71.26 487	91.76 205	55.08 419	76.09 458	41.06 526	87.02 443	82.54 457

WTY-MVS		67.91 460	68.35 456	66.58 491	80.82 430	48.12 502	65.96 508	72.60 459	53.67 479	71.20 488	81.68 456	58.97 376	69.06 492	48.57 502	81.67 497	82.55 456

test0.0.03 1		64.66 480	64.36 479	65.57 497	75.03 508	46.89 509	64.69 512	61.58 528	62.43 398	71.18 489	77.54 497	43.41 498	68.47 500	40.75 528	82.65 493	81.35 470

CostFormer		69.98 444	68.68 454	73.87 432	77.14 486	50.72 493	79.26 348	74.51 440	51.94 493	70.97 490	84.75 404	45.16 489	87.49 334	55.16 453	79.23 510	83.40 444

Syy-MVS		69.40 450	70.03 438	67.49 485	81.72 413	38.94 534	71.00 476	61.99 521	61.38 412	70.81 491	72.36 525	61.37 358	79.30 438	64.50 369	85.18 465	84.22 429

myMVS_eth3d		64.66 480	63.89 481	66.97 489	81.72 413	37.39 537	71.00 476	61.99 521	61.38 412	70.81 491	72.36 525	20.96 549	79.30 438	49.59 495	85.18 465	84.22 429

testing91		69.94 445	68.99 450	72.80 444	83.81 377	45.89 513	71.57 473	73.64 450	68.24 305	70.77 493	77.82 493	34.37 519	84.44 398	53.64 466	87.00 444	88.07 370

GLUNet-SfM		36.71 510	36.32 513	37.87 527	23.81 553	32.04 544	38.61 541	29.05 552	18.10 545	70.60 494	50.66 542	18.79 551	40.81 548	17.68 548	59.57 542	40.74 542

testing99		69.27 451	68.15 458	72.63 446	83.29 391	45.45 515	71.15 475	71.08 473	67.34 323	70.43 495	77.77 495	32.24 525	84.35 400	53.72 464	86.33 452	88.10 369

tpmvs		70.16 439	69.56 443	71.96 454	74.71 510	48.13 501	79.63 333	75.45 436	65.02 363	70.26 496	81.88 453	45.34 486	85.68 384	58.34 419	75.39 523	82.08 464

sss		66.92 464	67.26 462	65.90 494	77.23 485	51.10 492	64.79 511	71.72 470	52.12 492	70.13 497	80.18 473	57.96 389	65.36 523	50.21 490	81.01 503	81.25 473

tpm2		68.45 458	66.83 466	73.30 440	78.93 467	48.50 500	79.76 332	71.76 469	47.50 510	69.92 498	83.60 424	42.07 503	88.40 316	48.44 504	79.51 507	83.01 451

myMVS_eth3d28		65.83 475	65.85 471	65.78 495	83.42 385	35.71 540	67.29 502	68.01 489	67.58 320	69.80 499	77.72 496	32.29 524	74.30 468	37.49 535	89.06 405	87.32 389

testing222		66.93 463	65.30 477	71.81 455	83.38 386	45.83 514	72.06 467	67.50 491	64.12 373	69.68 500	76.37 508	27.34 542	83.00 409	38.88 530	88.38 417	86.62 400

HY-MVS	64.64 18	73.03 404	72.47 407	74.71 426	83.36 388	54.19 466	82.14 283	81.96 375	56.76 459	69.57 501	86.21 377	60.03 366	84.83 393	49.58 496	82.65 493	85.11 417

dmvs_re		66.81 467	66.98 464	66.28 492	76.87 489	58.68 422	71.66 471	72.24 462	60.29 432	69.52 502	73.53 521	52.38 435	64.40 529	44.90 518	81.44 500	75.76 512

ETVMVS		64.67 479	63.34 487	68.64 477	83.44 384	41.89 527	69.56 490	61.70 526	61.33 414	68.74 503	75.76 510	28.76 537	79.35 437	34.65 538	86.16 456	84.67 422

tpm cat1		66.76 468	65.21 478	71.42 457	77.09 487	50.62 494	78.01 370	73.68 449	44.89 521	68.64 504	79.00 483	45.51 483	82.42 414	49.91 493	70.15 533	81.23 475

IB-MVS	62.13 19	71.64 423	68.97 451	79.66 329	80.80 431	62.26 349	73.94 443	76.90 424	63.27 383	68.63 505	76.79 504	33.83 520	91.84 192	59.28 413	87.26 436	84.88 419
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
EPNet		80.37 285	78.41 319	86.23 126	76.75 490	73.28 182	87.18 126	77.45 416	76.24 152	68.14 506	88.93 314	65.41 331	93.85 120	69.47 310	96.12 133	91.55 272
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dtuonly		66.56 469	67.23 463	64.55 501	69.44 534	43.53 523	66.34 507	72.11 465	48.23 509	68.04 507	83.21 432	55.95 407	66.59 516	55.55 447	86.17 455	83.53 440

PVSNet	58.17 21	66.41 471	65.63 475	68.75 476	81.96 407	49.88 497	62.19 521	72.51 461	51.03 498	68.04 507	75.34 516	50.84 447	74.77 464	45.82 517	82.96 488	81.60 468

tpmrst		66.28 472	66.69 468	65.05 500	72.82 523	39.33 533	78.20 366	70.69 476	53.16 483	67.88 509	80.36 472	48.18 460	74.75 465	58.13 421	70.79 532	81.08 476

CANet_DTU		77.81 329	77.05 336	80.09 321	81.37 420	59.90 395	83.26 239	88.29 261	69.16 286	67.83 510	83.72 422	60.93 359	89.47 282	69.22 314	89.70 391	90.88 291

EPMVS		62.47 488	62.63 490	62.01 508	70.63 531	38.74 535	74.76 429	52.86 542	53.91 477	67.71 511	80.01 474	39.40 508	66.60 515	55.54 448	68.81 538	80.68 480

UBG		64.34 483	63.35 486	67.30 487	83.50 381	40.53 531	67.46 500	65.02 506	54.77 472	67.54 512	74.47 519	32.99 523	78.50 447	40.82 527	83.58 484	82.88 452

MDTV_nov1_ep13			68.29 457		78.03 473	43.87 522	74.12 440	72.22 463	52.17 489	67.02 513	85.54 386	45.36 485	80.85 428	55.73 442	84.42 478

testing11		67.38 461	65.93 470	71.73 456	83.37 387	46.60 510	70.95 478	69.40 481	62.47 394	66.14 514	76.66 505	31.22 528	84.10 402	49.10 499	84.10 482	84.49 423

pmmvs3		62.47 488	60.02 500	69.80 467	71.58 528	64.00 317	70.52 482	58.44 536	39.77 535	66.05 515	75.84 509	27.10 544	72.28 472	46.15 515	84.77 477	73.11 519

ADS-MVSNet2		65.87 474	63.64 485	72.55 448	73.16 519	56.92 440	67.10 503	74.81 437	49.74 507	66.04 516	82.97 436	46.71 466	77.26 453	42.29 523	69.96 534	83.46 442

ADS-MVSNet		61.90 491	62.19 492	61.03 514	73.16 519	36.42 539	67.10 503	61.75 524	49.74 507	66.04 516	82.97 436	46.71 466	63.21 530	42.29 523	69.96 534	83.46 442

mvsany_test1		58.48 502	56.47 509	64.50 502	65.90 542	68.21 267	56.95 533	42.11 549	38.30 539	65.69 518	77.19 503	56.96 397	59.35 536	46.16 514	58.96 543	65.93 529

dmvs_testset		60.59 499	62.54 491	54.72 523	77.26 484	27.74 548	74.05 441	61.00 530	60.48 428	65.62 519	67.03 533	55.93 408	68.23 502	32.07 542	69.46 537	68.17 526

DSMNet-mixed		60.98 497	61.61 494	59.09 520	72.88 522	45.05 518	74.70 430	46.61 547	26.20 544	65.34 520	90.32 272	55.46 414	63.12 531	41.72 525	81.30 502	69.09 525

JIA-IIPM		69.41 449	66.64 469	77.70 374	73.19 518	71.24 222	75.67 415	65.56 504	70.42 267	65.18 521	92.97 153	33.64 522	83.06 408	53.52 468	69.61 536	78.79 499

test-LLR		67.21 462	66.74 467	68.63 478	76.45 495	55.21 456	67.89 495	67.14 495	62.43 398	65.08 522	72.39 523	43.41 498	69.37 487	61.00 400	84.89 473	81.31 471

test-mter		65.00 478	63.79 483	68.63 478	76.45 495	55.21 456	67.89 495	67.14 495	50.98 499	65.08 522	72.39 523	28.27 539	69.37 487	61.00 400	84.89 473	81.31 471

PMMVS2		55.64 507	59.27 501	44.74 525	64.30 544	12.32 555	40.60 540	49.79 544	53.19 482	65.06 524	84.81 403	53.60 425	49.76 544	32.68 541	89.41 396	72.15 520

baseline2		69.77 446	66.89 465	78.41 356	79.51 458	58.09 427	76.23 408	69.57 480	57.50 451	64.82 525	77.45 499	46.02 472	88.44 314	53.08 470	77.83 515	88.70 359

gg-mvs-nofinetune		68.96 455	69.11 447	68.52 481	76.12 499	45.32 516	83.59 225	55.88 540	86.68 32	64.62 526	97.01 11	30.36 531	83.97 405	44.78 519	82.94 489	76.26 510

PAPM		71.77 420	70.06 437	76.92 391	86.39 308	53.97 467	76.62 400	86.62 298	53.44 480	63.97 527	84.73 405	57.79 392	92.34 177	39.65 529	81.33 501	84.45 425

PDCNetPlus		57.49 504	56.93 507	59.15 519	56.36 550	47.35 508	52.32 538	77.34 419	39.50 537	63.50 528	73.19 522	13.19 554	56.86 539	47.51 508	89.48 394	73.22 518

new_pmnet		55.69 506	57.66 506	49.76 524	75.47 504	30.59 546	59.56 525	51.45 543	43.62 527	62.49 529	75.48 514	40.96 506	49.15 545	37.39 536	72.52 528	69.55 524

UWE-MVS-28		58.44 503	57.71 505	60.65 515	73.58 516	31.23 545	69.68 489	48.80 545	53.12 484	61.79 530	78.83 485	30.98 529	68.40 501	21.58 545	80.99 504	82.33 461

MDTV_nov1_ep13_2view						27.60 549	70.76 481		46.47 516	61.27 531		45.20 487		49.18 498		83.75 438

dp		60.70 498	60.29 499	61.92 510	72.04 526	38.67 536	70.83 480	64.08 511	51.28 496	60.75 532	77.28 500	36.59 516	71.58 477	47.41 509	62.34 541	75.52 513

TESTMET0.1,1		61.29 494	60.32 498	64.19 503	72.06 525	51.30 488	67.89 495	62.09 520	45.27 519	60.65 533	69.01 530	27.93 540	64.74 527	56.31 437	81.65 499	76.53 509

0.4-1-1-0.1		64.02 485	60.59 496	74.31 429	73.99 511	55.62 450	67.66 499	72.78 458	55.53 466	60.35 534	58.45 538	29.26 535	86.88 349	52.84 476	74.42 525	80.42 484

PMMVS		61.65 492	60.38 497	65.47 498	65.40 543	69.26 250	63.97 517	61.73 525	36.80 543	60.11 535	68.43 531	59.42 372	66.35 517	48.97 500	78.57 514	60.81 536

PVSNet_0	51.08 22	56.10 505	54.97 510	59.48 518	75.12 507	53.28 474	55.16 535	61.89 523	44.30 523	59.16 536	62.48 536	54.22 422	65.91 520	35.40 537	47.01 544	59.25 538

MVS-HIRNet		61.16 495	62.92 489	55.87 521	79.09 464	35.34 541	71.83 468	57.98 537	46.56 515	59.05 537	91.14 231	49.95 456	76.43 456	38.74 531	71.92 531	55.84 540

E-PMN		61.59 493	61.62 493	61.49 512	66.81 538	55.40 454	53.77 536	60.34 531	66.80 331	58.90 538	65.50 534	40.48 507	66.12 518	55.72 443	86.25 453	62.95 534

GG-mvs-BLEND				67.16 488	73.36 517	46.54 512	84.15 205	55.04 541		58.64 539	61.95 537	29.93 532	83.87 406	38.71 532	76.92 521	71.07 522

EPNet_dtu		72.87 406	71.33 418	77.49 380	77.72 477	60.55 384	82.35 274	75.79 431	66.49 335	58.39 540	81.06 462	53.68 424	85.98 372	53.55 467	92.97 281	85.95 407
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		41.90 509	42.65 512	39.67 526	70.86 529	21.11 550	61.01 524	21.42 555	57.36 452	57.97 541	50.06 543	16.40 552	58.73 537	21.03 546	27.69 548	39.17 543

0.4-1-1-0.2		62.43 490	58.81 504	73.31 439	70.85 530	54.20 465	64.36 514	72.99 455	53.70 478	57.51 542	54.59 540	29.52 533	86.44 362	51.70 488	74.02 526	79.30 493

0.3-1-1-0.015		62.57 487	58.82 503	73.82 434	71.85 527	54.96 459	65.63 509	72.97 456	54.16 475	56.95 543	55.43 539	26.76 545	86.59 358	52.05 481	73.55 527	79.92 488

EMVS		61.10 496	60.81 495	61.99 509	65.96 541	55.86 447	53.10 537	58.97 535	67.06 328	56.89 544	63.33 535	40.98 505	67.03 512	54.79 457	86.18 454	63.08 533

CHOSEN 280x420		59.08 501	56.52 508	66.76 490	76.51 493	64.39 313	49.62 539	59.00 534	43.86 525	55.66 545	68.41 532	35.55 518	68.21 503	43.25 521	76.78 522	67.69 528

MVE	40.22 23	51.82 508	50.47 511	55.87 521	62.66 547	51.91 483	31.61 543	39.28 550	40.65 533	50.76 546	74.98 518	56.24 402	44.67 546	33.94 540	64.11 540	71.04 523
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
kuosan		30.83 511	32.17 514	26.83 529	53.36 551	19.02 553	57.90 531	20.44 556	38.29 540	38.01 547	37.82 545	15.18 553	33.45 549	7.74 549	20.76 549	28.03 544

DeepMVS_CX				24.13 530	32.95 552	29.49 547		21.63 554	12.07 546	37.95 548	45.07 544	30.84 530	19.21 550	17.94 547	33.06 547	23.69 545

tmp_tt		20.25 514	24.50 517	7.49 531	4.47 555	8.70 556	34.17 542	25.16 553	1.00 549	32.43 549	18.49 546	39.37 509	9.21 551	21.64 544	43.75 545	4.57 546

test_method		30.46 512	29.60 515	33.06 528	17.99 554	3.84 557	13.62 544	73.92 444	2.79 547	18.29 550	53.41 541	28.53 538	43.25 547	22.56 543	35.27 546	52.11 541

EGC-MVSNET		74.79 381	69.99 439	89.19 66	94.89 37	87.00 19	91.89 42	86.28 301	1.09 548	2.23 551	95.98 29	81.87 137	89.48 281	79.76 141	95.96 141	91.10 282

testmvs		5.91 518	7.65 521	0.72 533	1.20 556	0.37 559	59.14 527	0.67 558	0.49 551	1.11 552	2.76 550	0.94 556	0.24 553	1.02 551	1.47 550	1.55 548

test123		6.27 517	8.08 520	0.84 532	1.11 557	0.57 558	62.90 518	0.82 557	0.54 550	1.07 553	2.75 551	1.26 555	0.30 552	1.04 550	1.26 551	1.66 547

mmdepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

monomultidepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

test_blank		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uanet_test		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

DCPMVS		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

cdsmvs_eth3d_5k		20.81 513	27.75 516	0.00 534	0.00 558	0.00 560	0.00 545	85.44 318	0.00 552	0.00 554	82.82 441	81.46 143	0.00 554	0.00 552	0.00 552	0.00 549

pcd_1.5k_mvsjas		6.41 516	8.55 519	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	76.94 203	0.00 554	0.00 552	0.00 552	0.00 549

sosnet-low-res		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

sosnet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uncertanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

Regformer		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

ab-mvs-re		6.65 515	8.87 518	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	79.80 476	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

WAC-MVS						37.39 537								52.61 478

MSC_two_6792asdad				88.81 72	91.55 141	77.99 126		91.01 181					96.05 8	87.45 28	98.17 36	92.40 229

No_MVS				88.81 72	91.55 141	77.99 126		91.01 181					96.05 8	87.45 28	98.17 36	92.40 229

eth-test2					0.00 558

eth-test					0.00 558

OPU-MVS				88.27 88	91.89 125	77.83 129	90.47 60				91.22 227	81.12 147	94.68 82	74.48 230	95.35 171	92.29 240

save fliter					93.75 67	77.44 136	86.31 147	89.72 227	70.80 263

test_0728_SECOND				86.79 114	94.25 52	72.45 201	90.54 57	94.10 40					95.88 17	86.42 46	97.97 48	92.02 254

GSMVS																83.88 433

sam_mvs1												46.11 471				83.88 433

sam_mvs												45.92 477

MTGPA								91.81 153

test_post1							78.85 358				3.13 548	45.19 488	80.13 434	58.11 422

test_post											3.10 549	45.43 484	77.22 454

patchmatchnet-post											81.71 455	45.93 476	87.01 344

MTMP							90.66 53	33.14 551

gm-plane-assit					75.42 505	44.97 519			52.17 489		72.36 525		87.90 326	54.10 460

test9_res														80.83 130	96.45 117	90.57 303

agg_prior2														79.68 143	96.16 130	90.22 312

test_prior4						78.97 115	84.59 192

test_prior				86.32 123	90.59 172	71.99 209		92.85 114					94.17 107			92.80 202

新几何2							81.72 290

旧先验1					91.97 121	71.77 210		81.78 378			91.84 199	73.92 251			93.65 254	83.61 439

无先验							82.81 258	85.62 316	58.09 445				91.41 207	67.95 332		84.48 424

原ACMM2							82.26 279

testdata2													86.43 363	63.52 376

segment_acmp												81.94 133

testdata1							79.62 334		73.95 194

plane_prior7					93.45 74	77.31 139

plane_prior6					92.61 99	76.54 146						74.84 232

plane_prior5								93.61 70					95.22 62	80.78 131	95.83 152	94.46 104

plane_prior4											92.95 154

plane_prior2							89.45 87		79.44 112

plane_prior1					92.83 96

plane_prior						76.42 149	87.15 128		75.94 159						95.03 188

n2								0.00 559

nn								0.00 559

door-mid								74.45 441

test11								91.46 162

door								72.57 460

HQP5-MVS						70.66 228

BP-MVS														77.30 187

HQP3-MVS								92.68 120							94.47 218

HQP2-MVS												72.10 281

NP-MVS					91.95 122	74.55 172					90.17 281

ACMMP++_ref															95.74 159

ACMMP++															97.35 84

Test By Simon												79.09 168

High-resolution multi-view benchmark