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	84.21 193	96.51 7	57.84 432	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	84.47 182	96.56 6	58.83 421	89.04 94	92.74 119	91.40 5	96.12 4	96.06 28	87.23 52	95.57 43	79.42 149	98.74 5	99.00 2

LCM-MVSNet-Re		83.48 208	85.06 155	78.75 350	85.94 329	55.75 450	80.05 329	94.27 25	76.47 149	96.09 5	94.54 72	83.31 104	89.75 280	59.95 408	94.89 195	90.75 295

PEN-MVS		90.03 48	91.88 19	84.48 181	96.57 5	58.88 418	88.95 95	93.19 94	91.62 4	96.01 6	96.16 26	87.02 55	95.60 42	78.69 158	98.72 8	98.97 3

CP-MVSNet		89.27 65	90.91 46	84.37 183	96.34 8	58.61 424	88.66 103	92.06 142	90.78 6	95.67 7	95.17 50	81.80 139	95.54 46	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 38	89.60 4	98.27 27	92.08 252

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	93.16 154	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	85.71 145	96.32 9	62.39 346	89.54 84	93.31 88	90.21 11	95.57 10	95.66 36	81.42 144	95.90 17	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 28	89.13 6	98.26 29	91.76 263

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 28	89.13 6	98.26 29	91.76 263

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 77	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	90.20 215	69.87 276	95.06 14	96.14 27	84.28 92	93.07 158	87.68 23	96.34 121	97.09 20

wuyk23d		75.13 372	79.30 304	62.63 507	75.56 503	75.18 168	80.89 314	73.10 455	75.06 176	94.76 15	95.32 44	87.73 47	52.85 542	34.16 540	97.11 91	59.85 538

ACMH	76.49 14	89.34 62	91.14 37	83.96 201	92.50 103	70.36 236	89.55 82	93.84 55	81.89 82	94.70 16	95.44 43	90.69 9	88.31 320	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	86.45 122	92.52 102	69.19 254	87.84 117	88.05 267	81.66 84	94.64 17	96.53 19	65.94 327	94.75 81	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	90.63 194	70.00 275	94.55 18	96.67 16	87.94 42	93.59 136	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 83	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	90.29 212	69.27 284	94.39 20	96.38 20	86.02 72	93.52 141	83.96 90	95.92 146	95.34 61

test_0402		88.65 74	89.58 63	85.88 140	92.55 101	72.22 205	84.01 209	89.44 237	88.63 19	94.38 21	95.77 31	86.38 67	93.59 136	79.84 140	95.21 177	91.82 261

RoMa-HiRes		85.97 122	85.47 144	87.48 100	91.66 134	89.37 4	87.18 126	83.89 349	71.47 252	94.29 22	91.35 221	75.59 220	81.39 423	76.88 193	96.92 97	91.68 268

UniMVSNet_ETH3D		89.12 68	90.72 49	84.31 190	97.00 2	64.33 315	89.67 79	88.38 258	88.84 16	94.29 22	97.57 7	90.48 14	91.26 213	72.57 277	97.65 69	97.34 15

v7n		90.13 42	90.96 44	87.65 99	91.95 122	71.06 226	89.99 69	93.05 103	86.53 34	94.29 22	96.27 22	82.69 112	94.08 111	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	90.08 218	71.54 249	94.28 25	96.54 18	81.57 142	94.27 98	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 89	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 26	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 51

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	91.70 267
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	93.44 145	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 67	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	92.96 161	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 49	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	86.29 125	94.16 57	72.56 197	90.54 57	91.01 182	83.61 64	93.75 36	94.65 66	89.76 19	95.78 34	86.42 46	97.97 48	90.55 306
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 34	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 47	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 47	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 18	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 26	86.03 56	97.82 56	92.04 254

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

aaatest				88.50 80	94.38 47	76.12 156	92.12 33	93.85 53	77.53 142	93.24 44	93.18 141		95.85 24	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 24	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 40	86.82 42	97.34 85	92.19 247

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 71	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	89.44 286	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	89.44 286	74.12 241	96.10 134	94.45 106

Anonymous20231211		88.40 76	89.62 62	84.73 172	90.46 174	65.27 302	88.86 97	93.02 107	87.15 29	93.05 50	97.10 10	82.28 125	92.02 187	76.70 194	97.99 45	96.88 26

RoMa-SfM		83.52 206	82.69 227	86.00 136	90.77 166	89.30 5	85.98 156	81.47 385	65.77 347	92.99 51	89.25 306	69.55 302	78.65 447	72.01 281	96.45 117	90.04 321

PMatch-Up-SfM		81.93 251	80.09 291	87.42 102	89.08 210	86.10 34	81.31 300	83.35 358	67.64 319	92.96 52	90.69 254	45.71 481	85.82 383	75.20 223	94.89 195	90.35 311

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 73	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	86.22 129	91.63 135	77.07 142	89.82 74	93.77 57	78.90 120	92.88 54	92.29 184	86.11 70	90.22 258	86.24 53	97.24 88	91.36 278
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 65	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	94.17 108	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	84.84 166	88.16 246	63.28 326	86.64 141	92.20 137	75.42 172	92.81 59	94.50 73	74.05 249	94.06 112	83.88 91	96.28 123	97.17 19

dcpmvs_2		84.23 176	85.14 153	81.50 285	88.61 229	61.98 354	82.90 257	93.11 99	68.66 299	92.77 60	92.39 176	78.50 174	87.63 334	76.99 191	92.30 308	94.90 78

v8		86.22 114	86.83 111	84.36 185	87.82 255	62.35 348	86.42 146	91.33 169	76.78 148	92.73 61	94.48 75	73.41 262	93.72 127	83.10 99	95.41 169	97.01 23

nrg030		87.85 88	88.49 82	85.91 138	90.07 185	69.73 244	87.86 116	94.20 31	74.04 192	92.70 62	94.66 65	85.88 73	91.50 201	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	93.84 123	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 59	88.06 15	98.15 38	95.95 45

K. test v3		85.14 145	84.73 163	86.37 123	91.13 158	69.63 246	85.45 171	76.68 428	84.06 58	92.44 66	96.99 12	62.03 356	94.65 85	80.58 134	93.24 271	94.83 89

aaEdge-Enhanced		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	93.18 141	88.02 41	95.47 52	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 41	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 86	85.52 67	97.51 82	94.30 117

PMatch-SfM		81.28 264	79.37 302	87.00 108	89.23 203	85.40 45	81.27 305	81.28 387	65.97 338	92.13 70	90.30 275	44.94 493	85.43 387	74.06 244	95.14 182	90.18 318

LoFTR		76.52 352	76.53 347	76.49 401	83.36 389	80.97 93	80.82 317	68.96 486	62.47 395	92.13 70	89.95 286	51.45 442	74.61 468	64.97 362	94.67 211	73.87 517

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 75	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	93.10 157	82.67 108	98.04 40	93.64 155

TranMVSNet+NR-MVSNet		87.86 87	88.76 81	85.18 158	94.02 62	64.13 316	84.38 200	91.29 170	84.88 49	92.06 74	93.84 113	86.45 64	93.73 126	73.22 267	98.66 10	97.69 9

DKM		82.99 221	82.10 237	85.66 146	90.69 170	88.83 9	82.94 254	78.86 406	66.54 334	92.02 75	88.74 320	67.79 313	78.28 449	74.39 231	96.96 95	89.85 326

MTAPA		91.52 18	91.60 23	91.29 29	96.59 4	86.29 28	92.02 38	91.81 154	84.07 57	92.00 76	94.40 81	86.63 60	95.28 62	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 54	89.27 5	97.87 55	93.27 174

FC-MVSNet-test		85.93 124	87.05 104	82.58 252	92.25 111	56.44 444	85.75 163	93.09 101	77.33 143	91.94 78	94.65 66	74.78 234	93.41 147	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 57	85.83 63	97.78 58

sc_t1		87.70 91	88.94 73	83.99 199	93.47 73	67.15 277	85.05 181	88.21 266	86.81 31	91.87 79	97.65 5	85.51 81	87.91 326	74.22 235	97.63 70	96.92 25

lessismore_v0				85.95 137	91.10 159	70.99 227		70.91 476		91.79 81	94.42 79	61.76 357	92.93 163	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 37	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 49	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 44	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 20	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 30	87.10 39	97.69 66	93.93 134

test_fmvsmvis_n_1920		85.22 140	85.36 149	84.81 168	85.80 332	76.13 155	85.15 179	92.32 134	61.40 412	91.33 88	90.85 248	83.76 99	86.16 371	84.31 87	93.28 269	92.15 250

ANet_high		83.17 217	85.68 140	75.65 416	81.24 422	45.26 518	79.94 331	92.91 112	83.83 59	91.33 88	96.88 15	80.25 159	85.92 375	68.89 320	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 20	88.65 9	97.96 50	94.12 126

casdiffmvs_mvg		86.72 103	87.51 95	84.36 185	87.09 288	65.22 303	84.16 205	94.23 28	77.89 134	91.28 91	93.66 123	84.35 91	92.71 167	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		83.22 215	82.10 237	86.59 118	91.79 132	88.73 10	82.92 255	77.76 414	69.00 293	91.15 92	89.69 294	63.65 348	81.20 427	76.19 205	96.70 107	89.86 325

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	93.19 140	86.22 68	95.97 13	82.23 114	97.18 90	90.45 308
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	92.89 157	87.27 51	93.78 125	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 39	87.28 35	98.39 22	92.55 218

FIs		85.35 139	86.27 122	82.60 251	91.86 126	57.31 437	85.10 180	93.05 103	75.83 162	91.02 96	93.97 104	73.57 257	92.91 165	73.97 246	98.02 43	97.58 12

Casviewmamba		88.12 82	88.82 79	86.03 135	89.14 206	68.35 265	86.40 147	94.70 17	79.80 105	90.92 97	93.72 121	87.83 44	93.81 124	81.09 125	95.75 157	95.92 47

UniMVSNet_NR-MVSNet		86.84 101	87.06 103	86.17 132	92.86 94	67.02 282	82.55 266	91.56 160	83.08 71	90.92 97	91.82 202	78.25 177	93.99 114	74.16 239	98.35 23	97.49 13

DU-MVS		86.80 102	86.99 107	86.21 130	93.24 84	67.02 282	83.16 247	92.21 136	81.73 83	90.92 97	91.97 193	77.20 197	93.99 114	74.16 239	98.35 23	97.61 10

tt0805		88.09 83	89.79 58	82.98 234	93.26 83	63.94 319	91.10 50	89.64 231	85.07 46	90.91 100	91.09 234	89.16 25	91.87 192	82.03 116	95.87 150	93.13 182

V42		83.47 209	83.37 207	83.75 208	83.16 397	63.33 325	81.31 300	90.23 214	69.51 281	90.91 100	90.81 250	74.16 245	92.29 181	80.06 137	90.22 383	95.62 55

tt0320-xc		86.67 105	88.41 84	81.44 288	93.45 74	60.44 386	83.96 211	88.50 253	87.26 28	90.90 102	97.90 3	85.61 78	86.40 365	70.14 304	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 20	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	91.91 149	84.26 55	90.87 104	93.92 111	82.18 127	89.29 290	73.75 250	94.81 205	93.70 150

tt0320		86.63 107	88.36 85	81.41 289	93.57 71	60.73 383	84.37 201	88.61 252	87.00 30	90.75 105	97.98 2	85.54 80	86.45 362	69.75 309	97.70 65	97.06 22

WR-MVS		83.56 203	84.40 181	81.06 297	93.43 77	54.88 461	78.67 362	85.02 330	81.24 88	90.74 106	91.56 212	72.85 271	91.08 224	68.00 331	98.04 40	97.23 17

v1240		84.30 172	84.51 177	83.65 212	87.65 264	61.26 369	82.85 258	91.54 161	67.94 312	90.68 107	90.65 260	71.71 289	93.64 130	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 78	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 78	88.19 13	95.92 146	96.80 27

ZD-MVS					92.22 113	80.48 97		91.85 150	71.22 257	90.38 110	92.98 151	86.06 71	96.11 6	81.99 118	96.75 105

MIMVSNet1		83.63 200	84.59 172	80.74 303	94.06 61	62.77 334	82.72 260	84.53 342	77.57 140	90.34 111	95.92 30	76.88 209	85.83 382	61.88 393	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 57	80.87 129	95.50 168	94.53 101

KD-MVS_self_test		81.93 251	83.14 214	78.30 361	84.75 356	52.75 477	80.37 326	89.42 238	70.24 273	90.26 113	93.39 130	74.55 241	86.77 355	68.61 326	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	89.57 234	88.51 20	90.11 114	95.12 52	90.98 7	88.92 295	77.55 181	97.07 92	83.13 451
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PC_three_1452									58.96 440	90.06 115	91.33 222	80.66 154	93.03 160	75.78 212	95.94 144	92.48 221

v1921920		84.23 176	84.37 182	83.79 206	87.64 265	61.71 360	82.91 256	91.20 176	67.94 312	90.06 115	90.34 269	72.04 284	93.59 136	82.32 112	94.91 193	96.07 40

ITE_SJBPF				90.11 48	90.72 168	84.97 50		90.30 210	81.56 85	90.02 117	91.20 230	82.40 118	90.81 237	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 30	87.35 32	97.62 72	94.20 118

X-MVStestdata		85.04 149	82.70 226	92.08 8	95.64 23	86.25 29	92.64 20	93.33 85	85.07 46	89.99 118	16.05 548	86.57 61	95.80 30	87.35 32	97.62 72	94.20 118

v1192		84.57 162	84.69 168	84.21 193	87.75 259	62.88 330	83.02 250	91.43 164	69.08 290	89.98 120	90.89 245	72.70 274	93.62 134	82.41 111	94.97 192	96.13 38

Anonymous20240529		86.20 115	87.13 101	83.42 221	90.19 180	64.55 310	84.55 194	90.71 191	85.85 39	89.94 121	95.24 49	82.13 128	90.40 253	69.19 316	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	84.60 192	89.74 226	74.40 188	89.92 122	93.41 128	80.45 156	90.63 245	86.66 45	94.37 224	94.73 94

hybridcas		86.07 119	87.02 105	83.19 229	87.76 258	62.85 332	84.53 198	93.42 79	75.52 169	89.88 123	93.31 133	86.15 69	91.68 197	77.76 178	94.89 195	95.05 75

pmmvs6		86.52 109	88.06 88	81.90 272	92.22 113	62.28 349	84.66 191	89.15 243	83.54 66	89.85 124	97.32 8	88.08 40	86.80 354	70.43 301	97.30 87	96.62 31

v144192		84.24 175	84.41 180	83.71 210	87.59 267	61.57 361	82.95 253	91.03 181	67.82 316	89.80 125	90.49 266	73.28 266	93.51 142	81.88 121	94.89 195	96.04 42

v1144		84.54 166	84.72 165	84.00 198	87.67 263	62.55 338	82.97 252	90.93 186	70.32 270	89.80 125	90.99 238	73.50 258	93.48 143	81.69 122	94.65 213	95.97 43

MatchFormer		68.98 455	69.54 445	67.33 487	76.37 498	74.77 169	79.54 336	57.73 539	46.87 513	89.77 127	86.43 371	41.98 505	65.54 522	52.83 478	94.31 227	61.67 536

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 36	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	91.11 178	79.26 115	89.68 129	94.81 64	82.44 116	87.74 331	76.54 199	88.74 412	96.61 32

IU-MVS					94.18 54	72.64 193		90.82 189	56.98 457	89.67 130				85.78 64	97.92 51	93.28 173

FMVSNet1		84.55 165	85.45 146	81.85 274	90.27 178	61.05 373	86.83 135	88.27 263	78.57 126	89.66 131	95.64 37	75.43 222	90.68 242	69.09 317	95.33 172	93.82 143

DenseAffine		81.00 272	79.38 301	85.84 141	90.25 179	87.48 17	81.47 295	78.40 410	65.68 350	89.63 132	86.45 370	58.79 379	82.05 418	67.78 334	95.99 139	87.99 376

IterMVS-LS		84.73 159	84.98 157	83.96 201	87.35 276	63.66 320	83.25 241	89.88 224	76.06 153	89.62 133	92.37 180	73.40 264	92.52 172	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	92.87 158	84.56 88	93.89 120	77.65 179	96.62 109	90.70 298

UniMVSNet (Re)		86.87 99	86.98 108	86.55 120	93.11 87	68.48 264	83.80 219	92.87 113	80.37 97	89.61 135	91.81 203	77.72 185	94.18 106	75.00 226	98.53 15	96.99 24

IS-MVSNet		86.66 106	86.82 112	86.17 132	92.05 119	66.87 286	91.21 48	88.64 250	86.30 36	89.60 136	92.59 168	69.22 305	94.91 76	73.89 247	97.89 54	96.72 29

v2v482		84.09 179	84.24 186	83.62 213	87.13 283	61.40 364	82.71 261	89.71 229	72.19 239	89.55 137	91.41 218	70.70 296	93.20 152	81.02 127	93.76 247	96.25 36

Baseline_NR-MVSNet		84.00 187	85.90 132	78.29 362	91.47 146	53.44 473	82.29 277	87.00 296	79.06 118	89.55 137	95.72 35	77.20 197	86.14 372	72.30 279	98.51 16	95.28 64

ArgMatch-SfM		79.08 304	77.37 333	84.22 192	87.80 256	86.73 23	79.32 346	78.45 408	56.81 459	89.54 139	84.95 402	55.35 417	79.21 441	68.89 320	95.21 177	86.73 400

CSCG		86.26 112	86.47 115	85.60 148	90.87 164	74.26 174	87.98 114	91.85 150	80.35 98	89.54 139	88.01 334	79.09 168	92.13 183	75.51 217	95.06 187	90.41 309

ambc				82.98 234	90.55 173	64.86 306	88.20 108	89.15 243		89.40 141	93.96 107	71.67 290	91.38 209	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	83.41 236	92.38 131	70.25 272	89.35 142	90.68 256	82.85 111	94.57 89	79.55 146	95.95 143	92.00 256

LuminaMVS		83.94 190	83.51 199	85.23 156	89.78 191	71.74 212	84.76 187	87.27 281	72.60 230	89.31 143	90.60 264	64.04 341	90.95 228	79.08 153	94.11 234	92.99 193

MVStest1		70.05 443	69.26 446	72.41 452	58.62 550	55.59 452	76.61 402	65.58 504	53.44 481	89.28 144	93.32 132	22.91 549	71.44 479	74.08 243	89.52 394	90.21 317

ELoFTR		73.12 404	73.47 387	72.08 454	81.84 411	77.60 133	80.51 324	66.79 500	49.99 506	89.23 145	88.83 316	47.19 464	65.24 526	61.99 390	94.85 203	73.39 518

test_fmvsmconf0.01_n		86.68 104	86.52 114	87.18 104	85.94 329	78.30 121	86.93 131	92.20 137	65.94 340	89.16 146	93.16 144	83.10 105	89.89 274	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	92.25 186	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	85.91 157	93.60 72	80.16 101	89.13 148	93.44 127	83.82 96	90.98 227	83.86 92	95.30 176	93.60 159

fmvsm_s_conf0.5_n_10		85.20 142	85.25 152	85.02 163	86.01 327	71.31 221	84.96 182	91.76 156	69.10 288	88.90 149	92.56 171	73.84 253	90.63 245	86.88 40	93.26 270	93.13 182

MDA-MVSNet-bldmvs		77.47 334	76.90 341	79.16 341	79.03 466	64.59 307	66.58 507	75.67 434	73.15 217	88.86 150	88.99 314	66.94 319	81.23 426	64.71 364	88.22 424	91.64 270

EG-PatchMatch MVS		84.08 180	84.11 188	83.98 200	92.22 113	72.61 196	82.20 283	87.02 293	72.63 229	88.86 150	91.02 237	78.52 173	91.11 223	73.41 261	91.09 348	88.21 369

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 23	84.88 80	95.87 150	95.24 66

ArgMatch-Sym		78.58 318	76.86 342	83.71 210	87.61 266	86.40 27	78.19 368	77.45 417	55.72 464	88.82 153	82.01 453	59.68 372	78.75 446	67.43 336	94.86 201	85.98 406

fmvsm_s_conf0.5_n_5		84.56 163	84.71 166	84.11 197	87.92 252	72.09 207	84.80 183	88.64 250	64.43 370	88.77 154	91.78 205	78.07 179	87.95 325	85.85 62	92.18 316	92.30 238

EI-MVSNet-UG-set		85.04 149	84.44 179	86.85 113	83.87 377	72.52 199	83.82 217	85.15 326	80.27 100	88.75 155	85.45 391	79.95 162	91.90 190	81.92 120	90.80 364	96.13 38

EI-MVSNet-Vis-set		85.12 147	84.53 176	86.88 112	84.01 373	72.76 190	83.91 215	85.18 325	80.44 95	88.75 155	85.49 389	80.08 160	91.92 189	82.02 117	90.85 360	95.97 43

BridgeMVS		84.80 155	85.40 147	83.00 233	88.95 216	61.44 363	90.42 63	92.37 133	71.48 251	88.72 157	93.13 145	70.16 300	95.15 68	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	91.22 228	84.24 93	93.37 148	77.97 176	97.03 93	95.52 57

RRT-MVS		82.97 222	83.44 202	81.57 282	85.06 349	58.04 430	87.20 124	90.37 204	77.88 135	88.59 159	93.70 122	63.17 350	93.05 159	76.49 200	88.47 416	93.62 157

test_fmvsmconf0.1_n		86.18 117	85.88 133	87.08 106	85.26 345	78.25 122	85.82 161	91.82 152	65.33 357	88.55 160	92.35 183	82.62 115	89.80 276	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 91	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 56	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	83.58 215	87.97 248	67.13 278	87.55 119	94.32 22	73.44 207	88.47 163	87.54 350	86.45 64	91.06 225	75.76 213	93.76 247	92.54 219

canonicalmvs		85.50 129	86.14 125	83.58 215	87.97 248	67.13 278	87.55 119	94.32 22	73.44 207	88.47 163	87.54 350	86.45 64	91.06 225	75.76 213	93.76 247	92.54 219

NR-MVSNet		86.00 120	86.22 123	85.34 155	93.24 84	64.56 309	82.21 281	90.46 200	80.99 91	88.42 165	91.97 193	77.56 188	93.85 121	72.46 278	98.65 11	97.61 10

alignmvs		83.94 190	83.98 191	83.80 205	87.80 256	67.88 272	84.54 196	91.42 166	73.27 215	88.41 166	87.96 335	72.33 278	90.83 236	76.02 210	94.11 234	92.69 208

TransMVSNet (Re)		84.02 186	85.74 139	78.85 347	91.00 161	55.20 459	82.29 277	87.26 282	79.65 109	88.38 167	95.52 40	83.00 107	86.88 350	67.97 332	96.60 110	94.45 106

PM-MVS		80.20 292	79.00 306	83.78 207	88.17 244	86.66 25	81.31 300	66.81 499	69.64 278	88.33 168	90.19 279	64.58 335	83.63 408	71.99 282	90.03 386	81.06 479

fmvsm_s_conf0.5_n_3		86.19 116	87.27 99	82.95 236	86.91 296	70.38 235	85.31 175	92.61 125	75.59 167	88.32 169	92.87 158	82.22 126	88.63 309	88.80 8	92.82 287	89.83 327

tttt0517		81.07 270	79.58 298	85.52 150	88.99 215	66.45 291	87.03 130	75.51 436	73.76 196	88.32 169	90.20 278	37.96 514	94.16 110	79.36 151	95.13 183	95.93 46

FE-MVSNET2		82.80 225	83.51 199	80.67 308	89.08 210	58.46 425	82.40 274	89.26 239	71.25 256	88.24 171	94.07 99	75.75 218	89.56 281	65.91 351	95.67 163	93.98 131

casdiffmvs		85.21 141	85.85 134	83.31 224	86.17 321	62.77 334	83.03 249	93.93 47	74.69 181	88.21 172	92.68 167	82.29 124	91.89 191	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		71.42 427	70.67 429	73.64 438	69.66 534	70.46 233	66.97 506	89.73 227	42.68 532	88.20 173	83.04 436	43.77 497	60.07 534	65.35 358	86.66 448	90.39 310

SSC-MVS		77.55 333	81.64 249	65.29 500	90.46 174	20.33 553	73.56 450	68.28 488	85.44 40	88.18 174	94.64 69	70.93 294	81.33 424	71.25 288	92.03 320	94.20 118

balanced_ft_v1		83.49 207	83.93 193	82.19 264	86.46 306	59.61 402	90.81 52	90.92 187	71.78 246	88.08 175	92.56 171	66.97 318	94.54 92	75.34 221	92.42 304	92.42 225

MVSMamba_PlusPlus		87.53 93	88.86 77	83.54 219	92.03 120	62.26 350	91.49 45	92.62 123	88.07 24	88.07 176	96.17 25	72.24 280	95.79 33	84.85 81	94.16 233	92.58 216

MGCFI-Net		85.04 149	85.95 130	82.31 262	87.52 269	63.59 322	86.23 151	93.96 45	73.46 205	88.07 176	87.83 345	86.46 63	90.87 235	76.17 207	93.89 242	92.47 223

v148		82.31 235	82.48 233	81.81 277	85.59 338	59.66 400	81.47 295	86.02 309	72.85 224	88.05 178	90.65 260	70.73 295	90.91 232	75.15 224	91.79 328	94.87 80

AstraMVS		81.67 256	81.40 259	82.48 257	87.06 291	66.47 290	81.41 297	81.68 381	68.78 296	88.00 179	90.95 243	65.70 329	87.86 330	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	93.03 149	82.66 113	91.47 203	70.81 292	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	93.03 149	82.66 113	91.47 203	70.81 292	96.14 131	94.16 123

fmvsm_s_conf0.1_n_2		83.82 193	83.49 201	84.84 166	85.99 328	70.19 238	80.93 313	87.58 277	67.26 326	87.94 182	92.37 180	71.40 292	88.01 322	86.03 56	91.87 327	96.31 35

fmvsm_s_conf0.5_n_8		85.48 131	85.75 138	84.68 175	87.10 286	69.98 240	84.28 203	92.68 120	74.77 179	87.90 183	92.36 182	73.94 250	90.41 252	85.95 61	92.74 289	93.66 151

viewdifsd2359ckpt11		82.46 233	82.98 218	80.88 300	83.53 380	61.00 376	79.46 343	85.97 311	69.48 282	87.89 184	91.31 224	82.10 129	88.61 310	74.28 233	92.86 284	93.02 189

viewmsd2359difaftdt		82.46 233	82.99 217	80.88 300	83.52 381	61.00 376	79.46 343	85.97 311	69.48 282	87.89 184	91.31 224	82.10 129	88.61 310	74.28 233	92.86 284	93.02 189

pm-mvs1		83.69 197	84.95 159	79.91 324	90.04 187	59.66 400	82.43 272	87.44 278	75.52 169	87.85 186	95.26 48	81.25 146	85.65 386	68.74 324	96.04 136	94.42 110

PCF-MVS	74.62 15	82.15 243	80.92 271	85.84 141	89.43 198	72.30 203	80.53 323	91.82 152	57.36 453	87.81 187	89.92 289	77.67 186	93.63 131	58.69 417	95.08 186	91.58 272
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.5_n_2		83.62 201	83.29 208	84.62 176	85.43 342	70.18 239	80.61 322	87.24 283	67.14 327	87.79 188	91.87 195	71.79 288	87.98 324	86.00 60	91.77 330	95.71 50

guyue		81.57 258	81.37 261	82.15 266	86.39 309	66.13 294	81.54 294	83.21 360	69.79 277	87.77 189	89.95 286	65.36 333	87.64 333	75.88 211	92.49 302	92.67 209

KinetiMVS		85.95 123	86.10 127	85.50 152	87.56 268	69.78 242	83.70 222	89.83 225	80.42 96	87.76 190	93.24 139	73.76 255	91.54 200	85.03 75	93.62 256	95.19 69

mvs5depth		83.82 193	84.54 175	81.68 280	82.23 405	68.65 262	86.89 132	89.90 223	80.02 104	87.74 191	97.86 4	64.19 340	82.02 419	76.37 201	95.63 165	94.35 113

test_fmvsmconf_n		85.88 125	85.51 143	86.99 110	84.77 355	78.21 123	85.40 173	91.39 167	65.32 358	87.72 192	91.81 203	82.33 120	89.78 277	86.68 43	94.20 231	92.99 193

FMVSNet2		81.31 263	81.61 251	80.41 314	86.38 311	58.75 422	83.93 214	86.58 300	72.43 231	87.65 193	92.98 151	63.78 345	90.22 258	66.86 338	93.92 241	92.27 242

E5new		85.44 134	86.37 117	82.66 246	88.22 241	61.86 355	83.59 226	93.70 61	73.64 199	87.62 194	93.30 134	85.85 74	91.26 213	78.02 170	93.40 261	94.86 84

E5		85.44 134	86.37 117	82.66 246	88.22 241	61.86 355	83.59 226	93.70 61	73.64 199	87.62 194	93.30 134	85.85 74	91.26 213	78.02 170	93.40 261	94.86 84

E6new		85.44 134	86.37 117	82.66 246	88.23 239	61.86 355	83.59 226	93.69 64	73.64 199	87.61 196	93.30 134	85.85 74	91.26 213	78.02 170	93.40 261	94.86 84

E6		85.44 134	86.37 117	82.66 246	88.23 239	61.86 355	83.59 226	93.69 64	73.64 199	87.61 196	93.30 134	85.85 74	91.26 213	78.02 170	93.40 261	94.86 84

viewdifsd2359ckpt07		83.41 213	84.35 183	80.56 310	85.84 331	58.93 417	79.47 341	91.28 171	73.01 221	87.59 198	92.07 189	85.24 82	88.68 306	73.59 258	91.11 346	94.09 128

GeoE		85.45 133	85.81 135	84.37 183	90.08 183	67.07 281	85.86 160	91.39 167	72.33 236	87.59 198	90.25 276	84.85 86	92.37 177	78.00 174	91.94 324	93.66 151

VPA-MVSNet		83.47 209	84.73 163	79.69 329	90.29 177	57.52 435	81.30 303	88.69 249	76.29 151	87.58 200	94.44 76	80.60 155	87.20 343	66.60 343	96.82 102	94.34 114

casdiffseed414692147		85.64 128	86.08 128	84.32 188	87.49 271	65.55 301	85.81 162	93.00 110	75.85 161	87.50 201	93.40 129	83.10 105	91.71 196	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	92.38 177	81.42 144	93.28 150	83.07 100	97.24 88	91.67 269

VDDNet		84.35 170	85.39 148	81.25 291	95.13 31	59.32 406	85.42 172	81.11 388	86.41 35	87.41 203	96.21 24	73.61 256	90.61 247	66.33 345	96.85 99	93.81 146

VortexMVS		80.51 281	80.63 275	80.15 320	83.36 389	61.82 359	80.63 321	88.00 269	67.11 328	87.23 204	89.10 312	63.98 342	88.00 323	73.63 257	92.63 292	90.64 303

ALIKED-LG		78.19 325	77.07 336	81.54 283	84.95 350	86.95 20	86.16 153	83.96 348	56.64 461	87.21 205	90.05 285	51.36 443	78.05 451	57.73 427	95.60 166	79.63 491

c3_l		81.64 257	81.59 252	81.79 279	80.86 430	59.15 412	78.61 363	90.18 216	68.36 303	87.20 206	87.11 362	69.39 303	91.62 198	78.16 167	94.43 220	94.60 96

VDD-MVS		84.23 176	84.58 173	83.20 227	91.17 157	65.16 305	83.25 241	84.97 333	79.79 106	87.18 207	94.27 84	74.77 235	90.89 233	69.24 313	96.54 112	93.55 165

SIFT-NCMNet		71.70 423	70.97 426	73.90 432	77.55 482	81.03 91	71.58 473	63.31 517	63.91 379	87.12 208	81.00 464	50.00 455	64.64 529	49.37 498	94.86 201	76.04 512

MSLP-MVS++		85.00 152	86.03 129	81.90 272	91.84 129	71.56 219	86.75 139	93.02 107	75.95 158	87.12 208	89.39 300	77.98 180	89.40 289	77.46 183	94.78 206	84.75 422

baseline		85.20 142	85.93 131	83.02 232	86.30 316	62.37 347	84.55 194	93.96 45	74.48 185	87.12 208	92.03 192	82.30 122	91.94 188	78.39 160	94.21 229	94.74 93

YYNet1		70.06 442	70.44 433	68.90 475	73.76 515	53.42 474	58.99 530	67.20 495	58.42 443	87.10 211	85.39 393	59.82 370	67.32 511	59.79 409	83.50 487	85.96 407

MDA-MVSNet_test_wron		70.05 443	70.44 433	68.88 476	73.84 514	53.47 472	58.93 531	67.28 494	58.43 442	87.09 212	85.40 392	59.80 371	67.25 512	59.66 410	83.54 486	85.92 409

test_fmvs3		75.72 366	75.20 364	77.27 384	75.01 510	69.47 248	78.93 355	84.88 336	46.67 515	87.08 213	87.84 344	50.44 453	71.62 477	77.42 186	88.53 414	90.72 296

CNVR-MVS		87.81 89	87.68 92	88.21 89	92.87 92	77.30 140	85.25 176	91.23 175	77.31 144	87.07 214	91.47 217	82.94 108	94.71 82	84.67 84	96.27 125	92.62 212

EPP-MVSNet		85.47 132	85.04 156	86.77 115	91.52 144	69.37 249	91.63 44	87.98 270	81.51 86	87.05 215	91.83 201	66.18 326	95.29 60	70.75 295	96.89 98	95.64 54

TinyColmap		81.25 265	82.34 235	77.99 368	85.33 343	60.68 384	82.32 276	88.33 260	71.26 255	86.97 216	92.22 188	77.10 200	86.98 348	62.37 384	95.17 180	86.31 404

eth_miper_zixun_eth		80.84 275	80.22 285	82.71 244	81.41 420	60.98 379	77.81 376	90.14 217	67.31 325	86.95 217	87.24 359	64.26 338	92.31 179	75.23 222	91.61 335	94.85 88

E4		84.75 158	85.46 145	82.61 250	88.17 244	61.55 362	81.39 298	93.55 76	73.13 219	86.83 218	92.83 160	84.17 94	91.48 202	76.92 192	92.19 315	94.80 91

Anonymous20240521		80.18 293	81.25 263	76.95 391	83.15 398	60.84 381	82.46 269	85.99 310	68.76 297	86.78 219	93.73 120	59.13 376	77.44 453	73.71 251	97.55 78	92.56 217

Patchmatch-RL test		74.48 384	73.68 383	76.89 394	84.83 353	66.54 288	72.29 465	69.16 485	57.70 449	86.76 220	86.33 374	45.79 480	82.59 412	69.63 310	90.65 375	81.54 470

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	93.26 138	93.64 2	90.93 230	84.60 85	90.75 365	93.97 132

fmvsm_l_conf0.5_n_9		83.98 188	84.46 178	82.53 255	86.11 324	70.65 231	82.45 271	89.17 242	67.72 318	86.74 222	91.49 214	79.20 166	85.86 381	84.71 83	92.60 298	91.07 284

h-mvs33		84.25 174	82.76 224	88.72 74	91.82 131	82.60 75	84.00 210	84.98 332	71.27 253	86.70 223	90.55 265	63.04 353	93.92 119	78.26 165	94.20 231	89.63 331

hse-mvs2		83.47 209	81.81 246	88.47 81	91.03 160	82.27 79	82.61 262	83.69 353	71.27 253	86.70 223	86.05 380	63.04 353	92.41 175	78.26 165	93.62 256	90.71 297

HPM-MVS++		88.93 71	88.45 83	90.38 43	94.92 35	85.85 39	89.70 76	91.27 174	78.20 130	86.69 225	92.28 185	80.36 158	95.06 72	86.17 54	96.49 114	90.22 313

TSAR-MVS + MP.		88.14 80	87.82 91	89.09 68	95.72 21	76.74 145	92.49 26	91.19 177	67.85 315	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	85.36 154	90.14 182	69.52 247	86.17 152	91.58 158	74.41 186	86.55 227	91.49 214	78.54 171	93.97 116	73.71 251	93.21 274	92.59 215

EI-MVSNet		82.61 228	82.42 234	83.20 227	83.25 394	63.66 320	83.50 233	85.07 327	76.06 153	86.55 227	85.10 397	73.41 262	90.25 255	78.15 169	90.67 372	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	92.95 155	74.84 232	95.22 63	80.78 131	95.83 152	94.46 104

plane_prior3						76.85 144			77.79 137	86.55 227

BH-untuned		80.96 273	80.99 269	80.84 302	88.55 232	68.23 266	80.33 327	88.46 255	72.79 227	86.55 227	86.76 366	74.72 236	91.77 195	61.79 394	88.99 407	82.52 459

MVSTER		77.09 340	75.70 357	81.25 291	75.27 507	61.08 372	77.49 385	85.07 327	60.78 426	86.55 227	88.68 321	43.14 502	90.25 255	73.69 256	90.67 372	92.42 225

旧先验2							81.73 290		56.88 458	86.54 233			84.90 393	72.81 274

IterMVS-SCA-FT		80.64 279	79.41 299	84.34 187	83.93 375	69.66 245	76.28 408	81.09 389	72.43 231	86.47 234	90.19 279	60.46 363	93.15 155	77.45 184	86.39 452	90.22 313

WB-MVS		76.06 360	80.01 293	64.19 504	89.96 189	20.58 552	72.18 467	68.19 489	83.21 68	86.46 235	93.49 126	70.19 299	78.97 443	65.96 347	90.46 381	93.02 189

test_fmvsm_n_1920		83.60 202	82.89 220	85.74 144	85.22 346	77.74 131	84.12 207	90.48 198	59.87 437	86.45 236	91.12 233	75.65 219	85.89 379	82.28 113	90.87 357	93.58 161

PRO-TEST		83.72 196	82.74 225	86.65 116	87.95 250	71.80 210	86.50 145	91.93 147	69.23 285	86.38 237	93.36 131	65.66 330	95.92 15	72.80 275	90.86 359	92.22 245

fmvsm_s_conf0.5_n_4		84.38 168	84.27 185	84.74 171	87.25 279	70.84 228	83.55 231	88.45 256	68.64 300	86.29 238	91.31 224	74.97 229	88.42 316	87.87 19	90.07 385	94.95 77

DIV-MVS_self_test		80.43 283	80.23 283	81.02 298	79.99 451	59.25 408	77.07 391	87.02 293	67.38 322	86.19 239	89.22 308	63.09 351	90.16 262	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	83.85 216	92.01 143	65.91 342	86.19 239	91.75 207	83.77 98	94.98 74	77.43 185	96.71 106	93.73 149

cl____		80.42 284	80.23 283	81.02 298	79.99 451	59.25 408	77.07 391	87.02 293	67.37 323	86.18 241	89.21 309	63.08 352	90.16 262	76.31 203	95.80 154	93.65 154

MVS_111021_LR		84.28 173	83.76 196	85.83 143	89.23 203	83.07 70	80.99 311	83.56 355	72.71 228	86.07 242	89.07 313	81.75 141	86.19 370	77.11 189	93.36 265	88.24 368

viewmacassd2359aftdt		84.04 185	84.78 162	81.81 277	86.43 308	60.32 388	81.95 285	92.82 116	71.56 248	86.06 243	92.98 151	81.79 140	90.28 254	76.18 206	93.24 271	94.82 90

SP-DiffGlue		78.90 309	78.86 309	79.02 342	80.36 441	79.68 108	81.86 286	80.17 396	71.69 247	86.02 244	83.77 422	57.33 396	69.38 487	79.38 150	89.12 404	88.02 375

E2		84.06 181	84.61 170	82.40 260	87.49 271	61.31 366	81.03 309	93.36 81	71.83 244	86.02 244	91.87 195	82.91 109	91.37 210	75.66 215	91.33 341	94.53 101

E3		84.06 181	84.61 170	82.40 260	87.49 271	61.30 367	81.03 309	93.36 81	71.83 244	86.01 246	91.87 195	82.91 109	91.36 211	75.66 215	91.33 341	94.53 101

GBi-Net		82.02 247	82.07 239	81.85 274	86.38 311	61.05 373	86.83 135	88.27 263	72.43 231	86.00 247	95.64 37	63.78 345	90.68 242	65.95 348	93.34 266	93.82 143

test1		82.02 247	82.07 239	81.85 274	86.38 311	61.05 373	86.83 135	88.27 263	72.43 231	86.00 247	95.64 37	63.78 345	90.68 242	65.95 348	93.34 266	93.82 143

FMVSNet3		78.80 313	78.55 316	79.57 332	82.89 402	56.89 442	81.76 289	85.77 314	69.04 291	86.00 247	90.44 267	51.75 441	90.09 268	65.95 348	93.34 266	91.72 265

miper_ehance_all_eth		80.34 287	80.04 292	81.24 294	79.82 455	58.95 416	77.66 378	89.66 230	65.75 348	85.99 250	85.11 396	68.29 310	91.42 207	76.03 209	92.03 320	93.33 170

tfpnnormal		81.79 255	82.95 219	78.31 360	88.93 217	55.40 455	80.83 316	82.85 365	76.81 147	85.90 251	94.14 94	74.58 239	86.51 360	66.82 341	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	69.17 286	85.80 252	89.56 296	80.76 152	92.13 183	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		83.44 212	82.88 221	85.11 159	89.13 207	68.97 257	72.73 462	91.28 171	72.90 222	85.68 253	90.61 262	76.78 210	93.97 116	73.37 263	93.47 258	92.38 232

SSM_04072		81.44 261	82.88 221	77.10 387	89.13 207	68.97 257	72.73 462	91.28 171	72.90 222	85.68 253	90.61 262	76.78 210	69.94 485	73.37 263	93.47 258	92.38 232

SSM_0407		84.89 154	84.85 160	85.01 164	89.13 207	68.97 257	85.60 167	91.58 158	74.41 186	85.68 253	91.49 214	78.54 171	93.69 128	73.71 251	93.47 258	92.38 232

TSAR-MVS + GP.		83.95 189	82.69 227	87.72 97	89.27 202	81.45 89	83.72 221	81.58 384	74.73 180	85.66 256	86.06 379	72.56 276	92.69 169	75.44 219	95.21 177	89.01 354

EU-MVSNet		75.12 373	74.43 376	77.18 386	83.11 399	59.48 404	85.71 165	82.43 372	39.76 537	85.64 257	88.76 318	44.71 495	87.88 328	73.86 248	85.88 460	84.16 433

SIFT-ConvMatch		74.17 388	72.94 397	77.87 371	80.47 438	83.15 69	74.56 434	63.87 514	63.44 381	85.61 258	83.95 419	53.15 429	69.97 484	57.21 431	94.21 229	80.48 484

MonoMVSNet		76.66 347	77.26 335	74.86 424	79.86 454	54.34 465	86.26 150	86.08 306	71.08 259	85.59 259	88.68 321	53.95 424	85.93 374	63.86 372	80.02 507	84.32 428

LF4IMVS		82.75 227	81.93 244	85.19 157	82.08 406	80.15 102	85.53 168	88.76 247	68.01 309	85.58 260	87.75 346	71.80 287	86.85 352	74.02 245	93.87 243	88.58 361

Patchmtry		76.56 351	77.46 330	73.83 434	79.37 462	46.60 511	82.41 273	76.90 425	73.81 195	85.56 261	92.38 177	48.07 462	83.98 405	63.36 378	95.31 175	90.92 290

MVS_111021_HR		84.63 160	84.34 184	85.49 153	90.18 181	75.86 162	79.23 352	87.13 287	73.35 209	85.56 261	89.34 302	83.60 101	90.50 249	76.64 196	94.05 238	90.09 320

testdata				79.54 334	92.87 92	72.34 202		80.14 397	59.91 436	85.47 263	91.75 207	67.96 312	85.24 389	68.57 328	92.18 316	81.06 479

FE-MVSNET		78.46 320	79.36 303	75.75 413	86.53 302	54.53 463	78.03 369	85.35 321	69.01 292	85.41 264	90.68 256	64.27 337	85.73 384	62.59 383	92.35 307	87.00 395

viewcassd2359sk11		83.53 205	83.96 192	82.25 263	86.97 295	61.13 371	80.80 318	93.22 93	70.97 261	85.36 265	91.08 235	81.84 138	91.29 212	74.79 228	90.58 377	94.33 115

mvsmamba		80.30 289	78.87 308	84.58 178	88.12 247	67.55 274	92.35 30	84.88 336	63.15 385	85.33 266	90.91 244	50.71 449	95.20 66	66.36 344	87.98 426	90.99 287

SIFT-UM-Cal		73.50 398	72.76 400	75.71 415	79.21 464	81.68 85	72.85 461	68.91 487	62.93 386	85.31 267	83.39 432	52.88 431	67.56 510	54.97 456	94.42 223	77.89 506

test1111		78.53 319	78.85 311	77.56 376	92.22 113	47.49 506	82.61 262	69.24 484	72.43 231	85.28 268	94.20 90	51.91 438	90.07 270	65.36 357	96.45 117	95.11 73

thisisatest0530		79.07 305	77.33 334	84.26 191	87.13 283	64.58 308	83.66 224	75.95 431	68.86 295	85.22 269	87.36 356	38.10 511	93.57 139	75.47 218	94.28 228	94.62 95

XFeat-MNN		64.44 483	63.82 483	66.28 493	61.83 549	67.23 275	61.52 523	63.95 513	44.72 523	85.19 270	74.40 521	36.05 518	66.04 520	55.58 446	91.14 345	65.57 531

BP-MVS1		82.81 224	81.67 248	86.23 127	87.88 254	68.53 263	86.06 155	84.36 343	75.65 165	85.14 271	90.19 279	45.84 479	94.42 95	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	85.12 272	90.34 269	66.19 324	94.20 103	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	82.37 373	74.56 183	85.12 272	90.34 269	66.19 324	94.20 103	76.57 197	95.68 161	91.03 286

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	85.12 272	89.67 295	84.47 90	95.46 53	82.56 109	96.26 126	93.77 148

dtuonlycased		77.13 339	76.99 339	77.55 379	88.60 230	57.48 436	74.18 439	81.70 380	55.62 466	85.10 275	88.40 326	74.87 230	82.26 416	56.73 435	87.66 434	92.90 200

CLD-MVS		83.18 216	82.64 229	84.79 169	89.05 212	67.82 273	77.93 374	92.52 127	68.33 304	85.07 276	81.54 460	82.06 131	92.96 161	69.35 312	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		82.58 230	81.93 244	84.50 179	87.68 262	73.35 180	86.14 154	77.70 415	61.64 410	85.02 277	91.62 209	77.75 183	86.24 367	82.79 106	87.07 441	93.91 136

FA-MVS(test-final)		83.13 218	83.02 216	83.43 220	86.16 323	66.08 295	88.00 113	88.36 259	75.55 168	85.02 277	92.75 165	65.12 334	92.50 173	74.94 227	91.30 343	91.72 265

viewdifsd2359ckpt09		83.64 199	83.18 212	85.03 162	87.26 278	66.99 284	85.32 174	93.83 56	65.57 352	84.99 279	89.40 299	77.30 193	93.57 139	71.16 291	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	84.96 280	90.69 254	80.01 161	95.14 69	78.37 161	95.78 156	91.82 261
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	85.06 161	86.36 314	74.71 170	88.77 100	90.00 220	75.65 165	84.96 280	93.17 143	74.06 248	91.19 220	78.28 164	91.09 348	89.29 341

QAPM		82.59 229	82.59 231	82.58 252	86.44 307	66.69 287	89.94 72	90.36 205	67.97 311	84.94 282	92.58 170	72.71 273	92.18 182	70.63 298	87.73 431	88.85 356

fmvsm_l_conf0.5_n_3		85.11 148	84.96 158	85.56 149	87.49 271	75.69 163	84.71 189	90.61 196	67.64 319	84.88 283	92.05 190	82.30 122	88.36 318	83.84 93	91.10 347	92.62 212

VPNet		80.25 290	81.68 247	75.94 410	92.46 104	47.98 504	76.70 398	81.67 382	73.45 206	84.87 284	92.82 161	74.66 238	86.51 360	61.66 396	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	91.09 180	78.77 123	84.85 285	90.89 245	80.85 150	95.29 60	81.14 124	95.32 173	92.34 235

viewmanbaseed2359cas		82.95 223	83.43 203	81.52 284	85.18 347	60.03 393	81.36 299	92.38 131	69.55 280	84.84 286	91.38 219	79.85 164	90.09 268	74.22 235	92.09 318	94.43 109

SIFT-NCM-Cal		73.77 394	72.70 402	76.99 389	82.03 407	83.73 63	75.59 419	63.01 520	63.50 380	84.80 287	83.94 420	55.86 410	67.80 506	52.94 475	92.62 293	79.44 493

E3new		83.08 220	83.39 205	82.14 267	86.49 304	61.00 376	80.64 320	93.12 98	70.30 271	84.78 288	90.34 269	80.85 150	91.24 218	74.20 238	89.83 390	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	84.76 289	87.70 347	78.87 170	94.18 106	80.67 133	96.29 122	92.73 204

SIFT-UMatch		73.61 396	72.65 404	76.46 402	80.19 449	82.31 78	74.23 438	64.86 508	64.03 376	84.69 290	84.19 416	50.89 447	67.79 507	57.03 432	93.79 246	79.28 495

pmmvs-eth3d		78.42 324	77.04 338	82.57 254	87.44 275	74.41 173	80.86 315	79.67 399	55.68 465	84.69 290	90.31 274	60.91 361	85.42 388	62.20 386	91.59 336	87.88 381

test_prior2							83.37 237		75.43 171	84.58 292	91.57 211	81.92 136		79.54 147	96.97 94

fmvsm_s_conf0.5_n_6		84.05 183	84.14 187	83.81 204	87.75 259	71.17 224	83.42 235	91.10 179	67.90 314	84.53 293	90.70 253	73.01 269	88.73 303	85.09 72	93.72 252	91.53 275

fmvsm_s_conf0.5_n_a		82.21 239	81.51 257	84.32 188	86.56 301	73.35 180	85.46 170	77.30 421	61.81 406	84.51 294	90.88 247	77.36 191	86.21 369	82.72 107	86.97 446	93.38 168

TEST9					92.34 108	79.70 106	83.94 212	90.32 207	65.41 356	84.49 295	90.97 239	82.03 132	93.63 131

train_agg		85.98 121	85.28 151	88.07 93	92.34 108	79.70 106	83.94 212	90.32 207	65.79 344	84.49 295	90.97 239	81.93 134	93.63 131	81.21 123	96.54 112	90.88 292

fmvsm_s_conf0.1_n		82.17 241	81.59 252	83.94 203	86.87 299	71.57 218	85.19 178	77.42 419	62.27 401	84.47 297	91.33 222	76.43 213	85.91 377	83.14 97	87.14 439	94.33 115

Gipuma		84.44 167	86.33 121	78.78 349	84.20 368	73.57 178	89.55 82	90.44 201	84.24 56	84.38 298	94.89 56	76.35 216	80.40 434	76.14 208	96.80 104	82.36 461
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		64.31 485	65.85 472	59.67 518	66.54 540	62.24 352	57.76 533	70.96 475	40.13 535	84.36 299	82.09 450	46.93 465	51.67 543	61.99 390	81.89 497	65.12 532

test_8					92.09 117	78.87 116	83.82 217	90.31 209	65.79 344	84.36 299	90.96 241	81.93 134	93.44 145

SIFT-MNN		74.38 387	73.27 390	77.72 374	82.37 404	83.68 64	76.29 407	67.76 491	64.16 373	84.33 301	84.30 411	50.36 454	68.84 496	57.79 426	92.07 319	80.66 483

cl22		78.97 307	78.21 322	81.24 294	77.74 477	59.01 415	77.46 386	87.13 287	65.79 344	84.32 302	85.10 397	58.96 378	90.88 234	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	84.32 302	89.33 303	83.87 95	94.53 93	82.45 110	94.89 195	94.90 78

agg_prior					91.58 139	77.69 132		90.30 210		84.32 302			93.18 153

Anonymous202405211		80.51 281	81.19 267	78.49 355	88.48 233	57.26 438	76.63 400	82.49 369	81.21 89	84.30 305	92.24 187	67.99 311	86.24 367	62.22 385	95.13 183	91.98 258

LFMVS		80.15 294	80.56 277	78.89 344	89.19 205	55.93 446	85.22 177	73.78 448	82.96 72	84.28 306	92.72 166	57.38 394	90.07 270	63.80 373	95.75 157	90.68 299

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	84.27 307	94.05 100	78.35 176	93.65 129	80.54 135	91.58 337	92.08 252
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ECVR-MVS		78.44 323	78.63 315	77.88 370	91.85 127	48.95 500	83.68 223	69.91 480	72.30 237	84.26 308	94.20 90	51.89 439	89.82 275	63.58 374	96.02 137	94.87 80

FE-MVS		79.98 298	78.86 309	83.36 222	86.47 305	66.45 291	89.73 75	84.74 340	72.80 226	84.22 309	91.38 219	44.95 492	93.60 135	63.93 371	91.50 338	90.04 321

SIFT-PointCN		72.17 417	71.14 425	75.23 420	77.93 476	79.30 112	72.22 466	64.71 510	62.60 389	84.13 310	81.00 464	46.91 466	67.69 509	55.17 453	95.64 164	78.70 501

ETV-MVS		84.31 171	83.91 195	85.52 150	88.58 231	70.40 234	84.50 199	93.37 80	78.76 124	84.07 311	78.72 488	80.39 157	95.13 70	73.82 249	92.98 280	91.04 285

SIFT-PCN-Cal		71.86 419	71.21 423	73.82 435	77.43 483	78.37 120	71.75 470	65.73 503	62.15 403	84.04 312	81.59 459	50.59 451	64.96 527	52.46 480	95.15 181	78.14 505

fmvsm_s_conf0.5_n		81.91 253	81.30 262	83.75 208	86.02 326	71.56 219	84.73 188	77.11 424	62.44 398	84.00 313	90.68 256	76.42 214	85.89 379	83.14 97	87.11 440	93.81 146

MCST-MVS		84.36 169	83.93 193	85.63 147	91.59 136	71.58 217	83.52 232	92.13 139	61.82 405	83.96 314	89.75 292	79.93 163	93.46 144	78.33 163	94.34 225	91.87 260

新几何1				82.95 236	93.96 63	78.56 119		80.24 395	55.45 468	83.93 315	91.08 235	71.19 293	88.33 319	65.84 352	93.07 277	81.95 466

mmtdpeth		85.13 146	85.78 137	83.17 230	84.65 357	74.71 170	85.87 159	90.35 206	77.94 133	83.82 316	96.96 14	77.75 183	80.03 437	78.44 159	96.21 127	94.79 92

fmvsm_l_conf0.5_n		82.06 245	81.54 256	83.60 214	83.94 374	73.90 176	83.35 238	86.10 305	58.97 439	83.80 317	90.36 268	74.23 243	86.94 349	82.90 103	90.22 383	89.94 323

GDP-MVS		82.17 241	80.85 274	86.15 134	88.65 227	68.95 260	85.65 166	93.02 107	68.42 302	83.73 318	89.54 297	45.07 491	94.31 97	79.66 144	93.87 243	95.19 69

viewdifsd2359ckpt13		82.22 238	81.98 243	82.95 236	85.48 341	64.44 312	83.17 246	92.11 140	65.97 338	83.72 319	89.73 293	77.60 187	90.80 238	70.61 299	89.42 396	93.59 160

BH-RMVSNet		80.53 280	80.22 285	81.49 286	87.19 282	66.21 293	77.79 377	86.23 303	74.21 190	83.69 320	88.50 325	73.25 267	90.75 239	63.18 380	87.90 427	87.52 387

USDC		76.63 348	76.73 345	76.34 405	83.46 384	57.20 439	80.02 330	88.04 268	52.14 492	83.65 321	91.25 227	63.24 349	86.65 357	54.66 459	94.11 234	85.17 417

miper_enhance_ethall		77.83 328	76.93 340	80.51 311	76.15 499	58.01 431	75.47 422	88.82 245	58.05 447	83.59 322	80.69 467	64.41 336	91.20 219	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	86.76 297	84.54 52	83.58 323	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	87.13 283	91.15 2	87.70 118	88.42 257	74.57 182	83.56 324	85.65 385	78.49 175	94.21 102	72.04 280	92.88 283	94.05 129

CNLPA		83.55 204	83.10 215	84.90 165	89.34 200	83.87 61	84.54 196	88.77 246	79.09 117	83.54 325	88.66 324	74.87 230	81.73 421	66.84 340	92.29 310	89.11 347

SIFT-CM-Cal		73.20 403	71.85 412	77.25 385	79.80 456	82.49 77	73.51 451	64.83 509	62.27 401	83.49 326	82.81 444	51.79 440	69.71 486	53.70 466	94.43 220	79.53 492

SDMVSNet		81.90 254	83.17 213	78.10 365	88.81 222	62.45 345	76.08 412	86.05 308	73.67 197	83.41 327	93.04 147	82.35 119	80.65 431	70.06 306	95.03 188	91.21 280

sd_testset		79.95 299	81.39 260	75.64 417	88.81 222	58.07 429	76.16 411	82.81 366	73.67 197	83.41 327	93.04 147	80.96 149	77.65 452	58.62 418	95.03 188	91.21 280

viewmamba		81.97 250	82.13 236	81.47 287	80.43 439	62.46 340	79.31 347	89.99 222	71.08 259	83.39 329	90.21 277	78.08 178	88.73 303	77.55 181	89.16 403	93.23 178

diffmvs_AUTHOR		81.24 266	81.55 255	80.30 316	80.61 435	60.22 389	77.98 373	90.48 198	67.77 317	83.34 330	89.50 298	74.69 237	87.42 338	78.78 157	90.81 363	93.27 174

OpenMVS_ROB	70.19 17	77.77 331	77.46 330	78.71 351	84.39 364	61.15 370	81.18 307	82.52 368	62.45 397	83.34 330	87.37 355	66.20 323	88.66 308	64.69 365	85.02 470	86.32 403

thres100view900		75.45 369	75.05 369	76.66 398	87.27 277	51.88 485	81.07 308	73.26 453	75.68 164	83.25 332	86.37 373	45.54 482	88.80 298	51.98 484	90.99 350	89.31 338

miper_lstm_enhance		76.45 354	76.10 353	77.51 380	76.72 492	60.97 380	64.69 513	85.04 329	63.98 378	83.20 333	88.22 330	56.67 399	78.79 445	73.22 267	93.12 276	92.78 203

IterMVS		76.91 343	76.34 351	78.64 352	80.91 427	64.03 317	76.30 406	79.03 403	64.88 366	83.11 334	89.16 310	59.90 369	84.46 398	68.61 326	85.15 468	87.42 388
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres600view7		75.97 363	75.35 363	77.85 373	87.01 292	51.84 486	80.45 325	73.26 453	75.20 174	83.10 335	86.31 376	45.54 482	89.05 292	55.03 455	92.24 312	92.66 210

mvs_anonymous		78.13 326	78.76 313	76.23 408	79.24 463	50.31 496	78.69 361	84.82 338	61.60 411	83.09 336	92.82 161	73.89 252	87.01 345	68.33 330	86.41 451	91.37 277

MASt3R-SfM		63.18 487	63.70 485	61.64 512	63.57 546	67.13 278	64.25 516	57.31 540	37.50 543	82.96 337	80.95 466	45.96 476	49.82 544	54.93 457	85.89 459	67.95 528

fmvsm_l_conf0.5_n_a		81.46 260	80.87 273	83.25 225	83.73 379	73.21 185	83.00 251	85.59 318	58.22 445	82.96 337	90.09 284	72.30 279	86.65 357	81.97 119	89.95 388	89.88 324

SP-SuperGlue		80.13 295	80.14 287	80.11 321	79.95 453	80.97 93	80.94 312	80.77 392	76.46 150	82.92 339	85.73 384	58.75 380	70.83 481	85.20 70	90.50 378	88.53 362

dtuplus		78.46 320	78.13 324	79.45 337	80.90 429	59.52 403	77.65 379	86.72 298	61.21 419	82.91 340	89.26 305	73.46 261	87.27 342	63.53 376	87.49 436	91.55 273

test_fmvs2		73.57 397	72.80 398	75.90 411	72.74 525	68.84 261	77.07 391	84.32 345	45.14 521	82.89 341	84.22 415	48.37 460	70.36 483	73.40 262	87.03 443	88.52 363

MVS_Test		82.47 232	83.22 209	80.22 318	82.62 403	57.75 434	82.54 267	91.96 146	71.16 258	82.89 341	92.52 174	77.41 190	90.50 249	80.04 138	87.84 430	92.40 229

reproduce_monomvs		74.09 390	73.23 391	76.65 400	76.52 493	54.54 462	77.50 384	81.40 386	65.85 343	82.86 343	86.67 367	27.38 542	84.53 397	70.24 303	90.66 374	90.89 291

TestfortrainingZip				84.49 180	88.84 220	70.49 232	92.12 33	91.01 182	84.70 50	82.82 344	89.25 306	74.30 242	94.06 112		90.73 370	88.92 355

test12				86.57 119	90.74 167	72.63 195		90.69 192		82.76 345		79.20 166	94.80 80		95.32 173	92.27 242

fmvsm_s_conf0.5_n_11		84.56 163	84.69 168	84.15 196	86.53 302	71.29 222	85.53 168	92.62 123	70.54 266	82.75 346	91.20 230	77.33 192	88.55 314	83.80 94	91.93 325	92.61 214

原ACMM1				84.60 177	92.81 98	74.01 175		91.50 162	62.59 390	82.73 347	90.67 259	76.53 212	94.25 100	69.24 313	95.69 160	85.55 413

test_yl		78.71 316	78.51 317	79.32 339	84.32 365	58.84 419	78.38 364	85.33 322	75.99 156	82.49 348	86.57 368	58.01 388	90.02 272	62.74 381	92.73 290	89.10 348

DCV-MVSNet		78.71 316	78.51 317	79.32 339	84.32 365	58.84 419	78.38 364	85.33 322	75.99 156	82.49 348	86.57 368	58.01 388	90.02 272	62.74 381	92.73 290	89.10 348

diffmvs		80.40 285	80.48 280	80.17 319	79.02 467	60.04 391	77.54 382	90.28 213	66.65 333	82.40 350	87.33 357	73.50 258	87.35 340	77.98 175	89.62 393	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		78.80 313	78.47 319	79.78 325	80.26 447	59.28 407	77.31 388	87.13 287	60.42 430	82.37 351	88.67 323	74.58 239	87.87 329	67.78 334	87.73 431	92.19 247

test222					93.31 81	76.54 146	79.38 345	77.79 413	52.59 487	82.36 352	90.84 249	66.83 321			91.69 333	81.25 474

D2MVS		76.84 344	75.67 358	80.34 315	80.48 437	62.16 353	73.50 452	84.80 339	57.61 451	82.24 353	87.54 350	51.31 444	87.65 332	70.40 302	93.19 275	91.23 279

VNet		79.31 303	80.27 282	76.44 403	87.92 252	53.95 469	75.58 420	84.35 344	74.39 189	82.23 354	90.72 252	72.84 272	84.39 400	60.38 406	93.98 239	90.97 288

Vis-MVSNet (Re-imp)		77.82 329	77.79 328	77.92 369	88.82 221	51.29 490	83.28 239	71.97 468	74.04 192	82.23 354	89.78 291	57.38 394	89.41 288	57.22 430	95.41 169	93.05 188

API-MVS		82.28 236	82.61 230	81.30 290	86.29 317	69.79 241	88.71 101	87.67 276	78.42 128	82.15 356	84.15 418	77.98 180	91.59 199	65.39 356	92.75 288	82.51 460

icg_test_0407_2		78.46 320	79.68 296	74.78 426	85.76 333	62.46 340	68.51 494	87.91 271	65.23 359	82.12 357	87.92 339	77.27 195	72.67 472	71.67 283	90.74 366	89.20 342

IMVS_0407		81.08 269	81.23 265	80.62 309	85.76 333	62.46 340	82.46 269	87.91 271	65.23 359	82.12 357	87.92 339	77.27 195	90.18 260	71.67 283	90.74 366	89.20 342

IMVS_0403		80.93 274	81.00 268	80.72 305	85.76 333	62.46 340	81.82 288	87.91 271	65.23 359	82.07 359	87.92 339	75.91 217	90.50 249	71.67 283	90.74 366	89.20 342

DP-MVS Recon		84.05 183	83.22 209	86.52 121	91.73 133	75.27 167	83.23 244	92.40 129	72.04 241	82.04 360	88.33 329	77.91 182	93.95 118	66.17 346	95.12 185	90.34 312

onestephybrid01		81.22 267	80.90 272	82.18 265	80.05 450	64.49 311	79.47 341	89.23 240	69.10 288	81.96 361	89.27 304	75.02 227	89.12 291	73.71 251	90.24 382	92.92 199

MSDG		80.06 297	79.99 294	80.25 317	83.91 376	68.04 271	77.51 383	89.19 241	77.65 138	81.94 362	83.45 429	76.37 215	86.31 366	63.31 379	86.59 449	86.41 402

test2506		74.12 389	73.39 388	76.28 406	91.85 127	44.20 521	84.06 208	48.20 547	72.30 237	81.90 363	94.20 90	27.22 544	89.77 278	64.81 363	96.02 137	94.87 80

Fast-Effi-MVS+		81.04 271	80.57 276	82.46 258	87.50 270	63.22 327	78.37 366	89.63 232	68.01 309	81.87 364	82.08 451	82.31 121	92.65 170	67.10 337	88.30 423	91.51 276

testgi		72.36 413	74.61 372	65.59 497	80.56 436	42.82 527	68.29 495	73.35 452	66.87 331	81.84 365	89.93 288	72.08 283	66.92 514	46.05 517	92.54 300	87.01 394

tfpn200view9		74.86 379	74.23 377	76.74 397	86.24 318	52.12 482	79.24 350	73.87 446	73.34 210	81.82 366	84.60 408	46.02 473	88.80 298	51.98 484	90.99 350	89.31 338

thres400		75.14 371	74.23 377	77.86 372	86.24 318	52.12 482	79.24 350	73.87 446	73.34 210	81.82 366	84.60 408	46.02 473	88.80 298	51.98 484	90.99 350	92.66 210

CL-MVSNet_self_test		76.81 345	77.38 332	75.12 422	86.90 297	51.34 488	73.20 456	80.63 394	68.30 305	81.80 368	88.40 326	66.92 320	80.90 428	55.35 451	94.90 194	93.12 185

OpenMVS	76.72 13	81.98 249	82.00 242	81.93 271	84.42 363	68.22 267	88.50 107	89.48 235	66.92 330	81.80 368	91.86 198	72.59 275	90.16 262	71.19 290	91.25 344	87.40 389

SIFT-NN-CMatch		72.68 409	71.28 420	76.88 395	78.79 469	82.59 76	73.68 447	61.02 530	60.35 431	81.79 370	83.09 435	52.94 430	68.88 495	57.28 429	92.53 301	79.16 497

MGCNet		85.37 138	84.58 173	87.75 96	85.28 344	73.36 179	86.54 144	85.71 315	77.56 141	81.78 371	92.47 175	70.29 298	96.02 10	85.59 66	95.96 141	93.87 138

AdaColmap		83.66 198	83.69 197	83.57 217	90.05 186	72.26 204	86.29 149	90.00 220	78.19 131	81.65 372	87.16 360	83.40 103	94.24 101	61.69 395	94.76 209	84.21 432

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	81.64 373	87.25 358	82.43 117	94.53 93	77.65 179	96.46 116	94.14 125

DELS-MVS		81.44 261	81.25 263	82.03 269	84.27 367	62.87 331	76.47 405	92.49 128	70.97 261	81.64 373	83.83 421	75.03 226	92.70 168	74.29 232	92.22 314	90.51 307
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		79.92 300	79.74 295	80.46 312	80.22 448	81.52 88	81.28 304	81.81 378	75.89 160	81.60 375	84.90 403	55.82 411	71.10 480	85.62 65	90.47 379	88.76 358

SP-MNN		77.71 332	77.85 326	77.29 383	78.48 472	75.90 160	79.14 353	79.46 400	69.61 279	81.56 376	84.60 408	54.98 421	69.02 494	81.08 126	91.72 332	86.95 396

114514_t		83.10 219	82.54 232	84.77 170	92.90 91	69.10 256	86.65 140	90.62 195	54.66 474	81.46 377	90.81 250	76.98 202	94.38 96	72.62 276	96.18 129	90.82 294

TR-MVS		76.77 346	75.79 355	79.72 328	86.10 325	65.79 298	77.14 389	83.02 363	65.20 363	81.40 378	82.10 449	66.30 322	90.73 241	55.57 447	85.27 464	82.65 454

TAMVS		78.08 327	76.36 350	83.23 226	90.62 171	72.87 189	79.08 354	80.01 398	61.72 408	81.35 379	86.92 365	63.96 344	88.78 301	50.61 490	93.01 279	88.04 374

Effi-MVS+		83.90 192	84.01 190	83.57 217	87.22 281	65.61 300	86.55 143	92.40 129	78.64 125	81.34 380	84.18 417	83.65 100	92.93 163	74.22 235	87.87 428	92.17 249

hybridnocas07		79.65 302	79.65 297	79.63 331	78.06 473	59.34 405	77.00 395	88.72 248	66.51 335	81.08 381	89.36 301	72.35 277	87.12 344	74.56 229	89.20 401	92.44 224

testing3		71.53 426	70.79 428	73.77 437	88.89 219	41.86 529	76.60 403	59.12 534	72.83 225	80.97 382	82.08 451	19.80 551	87.33 341	65.12 359	91.68 334	92.13 251

new-patchmatchnet		70.10 441	73.37 389	60.29 517	81.23 423	16.95 555	59.54 527	74.62 439	62.93 386	80.97 382	87.93 338	62.83 355	71.90 475	55.24 452	95.01 191	92.00 256

SIFT-NN-PointCN		72.35 414	71.17 424	75.90 411	77.68 479	80.93 96	73.48 453	63.14 519	60.88 424	80.94 384	82.91 441	52.54 435	67.74 508	55.98 442	92.95 282	79.05 499

PVSNet_Blended_VisFu		81.55 259	80.49 279	84.70 174	91.58 139	73.24 184	84.21 204	91.67 157	62.86 388	80.94 384	87.16 360	67.27 316	92.87 166	69.82 308	88.94 409	87.99 376

BH-w/o		76.57 349	76.07 354	78.10 365	86.88 298	65.92 297	77.63 380	86.33 301	65.69 349	80.89 386	79.95 476	68.97 308	90.74 240	53.01 474	85.25 465	77.62 508

PAPM_NR		83.23 214	83.19 211	83.33 223	90.90 163	65.98 296	88.19 109	90.78 190	78.13 132	80.87 387	87.92 339	73.49 260	92.42 174	70.07 305	88.40 417	91.60 271

ab-mvs		79.67 301	80.56 277	76.99 389	88.48 233	56.93 440	84.70 190	86.06 307	68.95 294	80.78 388	93.08 146	75.30 224	84.62 395	56.78 434	90.90 355	89.43 336

XXY-MVS		74.44 386	76.19 352	69.21 473	84.61 358	52.43 481	71.70 471	77.18 423	60.73 427	80.60 389	90.96 241	75.44 221	69.35 490	56.13 440	88.33 419	85.86 410

HQP4-MVS										80.56 390			94.61 87			93.56 163

HQP-NCC					91.19 154		84.77 184		73.30 212	80.55 391

ACMP_Plane					91.19 154		84.77 184		73.30 212	80.55 391

HQP-MVS		84.61 161	84.06 189	86.27 126	91.19 154	70.66 229	84.77 184	92.68 120	73.30 212	80.55 391	90.17 282	72.10 281	94.61 87	77.30 187	94.47 218	93.56 163

ALIKED-MNN		76.42 355	75.39 362	79.52 335	84.57 359	84.06 60	84.33 202	82.48 370	49.85 507	80.53 394	88.35 328	54.52 422	77.10 456	56.89 433	96.96 95	77.39 509

hybrid		79.06 306	78.94 307	79.40 338	77.99 475	59.05 414	77.07 391	88.49 254	64.42 371	80.52 395	88.78 317	71.45 291	86.82 353	73.23 266	88.52 415	92.34 235

test_cas_vis1_n_1920		69.20 454	69.12 447	69.43 472	73.68 516	62.82 333	70.38 485	77.21 422	46.18 518	80.46 396	78.95 485	52.03 437	65.53 523	65.77 354	77.45 521	79.95 488

AUN-MVS		81.18 268	78.78 312	88.39 83	90.93 162	82.14 80	82.51 268	83.67 354	64.69 368	80.29 397	85.91 383	51.07 446	92.38 176	76.29 204	93.63 255	90.65 302

HyFIR lowres test		75.12 373	72.66 403	82.50 256	91.44 147	65.19 304	72.47 464	87.31 280	46.79 514	80.29 397	84.30 411	52.70 434	92.10 186	51.88 488	86.73 447	90.22 313

test20.03		73.75 395	74.59 374	71.22 459	81.11 424	51.12 492	70.15 486	72.10 467	70.42 267	80.28 399	91.50 213	64.21 339	74.72 467	46.96 513	94.58 214	87.82 384

mvsany_test3		65.48 478	62.97 489	73.03 444	69.99 533	76.17 154	64.83 511	43.71 549	43.68 527	80.25 400	87.05 364	52.83 433	63.09 533	51.92 487	72.44 530	79.84 490

SIFT-NN-UMatch		72.46 411	71.25 421	76.08 409	78.57 471	81.88 82	74.36 435	61.59 528	61.99 404	80.24 401	83.46 428	51.20 445	68.08 505	57.95 425	91.91 326	78.28 504

F-COLMAP		84.97 153	83.42 204	89.63 57	92.39 106	83.40 66	88.83 98	91.92 148	73.19 216	80.18 402	89.15 311	77.04 201	93.28 150	65.82 353	92.28 311	92.21 246

GA-MVS		75.83 364	74.61 372	79.48 336	81.87 409	59.25 408	73.42 454	82.88 364	68.68 298	79.75 403	81.80 455	50.62 450	89.46 284	66.85 339	85.64 461	89.72 328

xiu_mvs_v1_base_debu		80.84 275	80.14 287	82.93 239	88.31 236	71.73 213	79.53 337	87.17 284	65.43 353	79.59 404	82.73 445	76.94 203	90.14 265	73.22 267	88.33 419	86.90 397

xiu_mvs_v1_base		80.84 275	80.14 287	82.93 239	88.31 236	71.73 213	79.53 337	87.17 284	65.43 353	79.59 404	82.73 445	76.94 203	90.14 265	73.22 267	88.33 419	86.90 397

xiu_mvs_v1_base_debi		80.84 275	80.14 287	82.93 239	88.31 236	71.73 213	79.53 337	87.17 284	65.43 353	79.59 404	82.73 445	76.94 203	90.14 265	73.22 267	88.33 419	86.90 397

test_fmvs1_n		70.94 432	70.41 435	72.53 450	73.92 513	66.93 285	75.99 413	84.21 347	43.31 529	79.40 407	79.39 481	43.47 498	68.55 499	69.05 318	84.91 473	82.10 464

blended_shiyan8		76.05 361	75.11 365	78.86 346	81.76 412	59.18 411	75.09 426	83.81 350	64.70 367	79.37 408	78.35 491	58.30 384	88.68 306	62.03 389	92.56 299	88.73 359

blended_shiyan6		76.05 361	75.11 365	78.87 345	81.74 413	59.15 412	75.08 427	83.79 351	64.69 368	79.37 408	78.37 490	58.30 384	88.69 305	61.99 390	92.61 294	88.77 357

patch_mono-2		78.89 310	79.39 300	77.41 382	84.78 354	68.11 269	75.60 417	83.11 362	60.96 423	79.36 410	89.89 290	75.18 225	72.97 471	73.32 265	92.30 308	91.15 282

UnsupCasMVSNet_eth		71.63 425	72.30 409	69.62 470	76.47 495	52.70 479	70.03 487	80.97 390	59.18 438	79.36 410	88.21 331	60.50 362	69.12 492	58.33 421	77.62 519	87.04 393

ppachtmachnet_test		74.73 383	74.00 379	76.90 393	80.71 433	56.89 442	71.53 475	78.42 409	58.24 444	79.32 412	82.92 440	57.91 391	84.26 402	65.60 355	91.36 340	89.56 333

gbinet_0.2-2-1-0.02		76.14 358	74.88 370	79.92 323	80.33 446	60.02 394	75.80 415	82.44 371	66.36 337	79.24 413	75.07 518	56.11 407	90.17 261	64.60 368	93.95 240	89.58 332

MG-MVS		80.32 288	80.94 270	78.47 356	88.18 243	52.62 480	82.29 277	85.01 331	72.01 242	79.24 413	92.54 173	69.36 304	93.36 149	70.65 297	89.19 402	89.45 334

usedtu_dtu_shiyan2		78.92 308	78.15 323	81.25 291	91.33 148	73.10 186	80.75 319	79.00 405	74.19 191	79.17 415	92.04 191	67.17 317	81.33 424	42.86 523	96.81 103	89.31 338

Fast-Effi-MVS+-dtu		82.54 231	81.41 258	85.90 139	85.60 337	76.53 148	83.07 248	89.62 233	73.02 220	79.11 416	83.51 426	80.74 153	90.24 257	68.76 323	89.29 398	90.94 289

SSC-MVS3.2		73.90 392	75.67 358	68.61 481	84.11 370	41.28 530	64.17 517	72.83 458	72.09 240	79.08 417	87.94 336	70.31 297	73.89 470	55.99 441	94.49 217	90.67 301

CDS-MVSNet		77.32 336	75.40 360	83.06 231	89.00 214	72.48 200	77.90 375	82.17 375	60.81 425	78.94 418	83.49 427	59.30 374	88.76 302	54.64 460	92.37 306	87.93 380
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
baseline1		73.26 400	73.54 385	72.43 451	84.92 352	47.79 505	79.89 332	74.00 444	65.93 341	78.81 419	86.28 377	56.36 401	81.63 422	56.63 436	79.04 514	87.87 382

SIFT-NN-NCMNet		72.70 408	71.25 421	77.06 388	81.65 416	84.07 59	75.19 424	63.15 518	61.29 416	78.74 420	83.21 433	53.60 426	69.25 491	53.99 463	90.47 379	77.86 507

ttmdpeth		71.72 422	70.67 429	74.86 424	73.08 522	55.88 447	77.41 387	69.27 483	55.86 463	78.66 421	93.77 118	38.01 513	75.39 464	60.12 407	89.87 389	93.31 172

EIA-MVS		82.19 240	81.23 265	85.10 160	87.95 250	69.17 255	83.22 245	93.33 85	70.42 267	78.58 422	79.77 479	77.29 194	94.20 103	71.51 287	88.96 408	91.93 259

thres200		72.34 415	71.55 417	74.70 428	83.48 383	51.60 487	75.02 428	73.71 449	70.14 274	78.56 423	80.57 470	46.20 471	88.20 321	46.99 512	89.29 398	84.32 428

usedtu_dtu_shiyan1		75.70 367	75.08 367	77.56 376	84.10 371	55.50 453	73.58 448	84.89 334	62.48 392	78.16 424	84.24 413	58.14 386	87.47 336	59.35 412	90.82 361	89.72 328

FE-MVSNET3		75.70 367	75.08 367	77.56 376	84.10 371	55.50 453	73.58 448	84.89 334	62.48 392	78.16 424	84.24 413	58.14 386	87.47 336	59.34 413	90.82 361	89.72 328

fmvsm_s_conf0.5_n_7		82.04 246	82.05 241	82.01 270	86.98 294	71.07 225	78.70 360	89.45 236	68.07 308	78.14 426	91.61 210	74.19 244	85.92 375	79.61 145	91.73 331	89.05 351

our_test_3		71.85 420	71.59 414	72.62 448	80.71 433	53.78 470	69.72 489	71.71 472	58.80 441	78.03 427	80.51 472	56.61 400	78.84 444	62.20 386	86.04 458	85.23 416

KD-MVS_2432*1600		66.87 466	65.81 474	70.04 464	67.50 537	47.49 506	62.56 520	79.16 401	61.21 419	77.98 428	80.61 468	25.29 547	82.48 413	53.02 472	84.92 471	80.16 486

miper_refine_blended		66.87 466	65.81 474	70.04 464	67.50 537	47.49 506	62.56 520	79.16 401	61.21 419	77.98 428	80.61 468	25.29 547	82.48 413	53.02 472	84.92 471	80.16 486

jason		77.42 335	75.75 356	82.43 259	87.10 286	69.27 250	77.99 372	81.94 377	51.47 496	77.84 430	85.07 400	60.32 365	89.00 293	70.74 296	89.27 400	89.03 352
jason: jason.
MAR-MVS		80.24 291	78.74 314	84.73 172	86.87 299	78.18 124	85.75 163	87.81 275	65.67 351	77.84 430	78.50 489	73.79 254	90.53 248	61.59 397	90.87 357	85.49 415
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		72.29 416	72.00 410	73.14 442	88.63 228	85.00 49	74.65 432	67.39 493	71.94 243	77.80 432	87.66 348	50.48 452	75.83 461	49.95 493	79.51 508	58.58 540

test_fmvs1		69.57 449	69.05 449	71.14 461	69.15 536	65.77 299	73.98 443	83.32 359	42.83 531	77.77 433	78.27 493	43.39 501	68.50 500	68.39 329	84.38 480	79.15 498

pmmvs4		74.92 378	72.98 396	80.73 304	84.95 350	71.71 216	76.23 409	77.59 416	52.83 486	77.73 434	86.38 372	56.35 402	84.97 392	57.72 428	87.05 442	85.51 414

wanda-best-256-512		74.97 376	73.85 380	78.35 358	80.36 441	58.13 426	73.10 458	83.53 356	64.04 375	77.62 435	75.71 512	56.22 404	88.60 312	61.42 398	92.61 294	88.32 365

FE-blended-shiyan7		74.97 376	73.85 380	78.35 358	80.36 441	58.13 426	73.10 458	83.53 356	64.03 376	77.62 435	75.71 512	56.22 404	88.60 312	61.42 398	92.61 294	88.32 365

usedtu_blend_shiyan5		77.07 341	76.43 349	78.99 343	80.36 441	59.77 398	83.25 241	88.32 261	74.91 177	77.62 435	75.71 512	56.22 404	88.89 296	58.91 415	92.61 294	88.32 365

ET-MVSNet_ETH3D		75.28 370	72.77 399	82.81 243	83.03 400	68.11 269	77.09 390	76.51 429	60.67 428	77.60 438	80.52 471	38.04 512	91.15 222	70.78 294	90.68 371	89.17 346

testing3-2		70.72 436	70.97 426	69.95 466	88.93 217	34.80 543	69.85 488	66.59 501	78.42 128	77.58 439	85.55 386	31.83 528	82.08 417	46.28 514	93.73 251	92.98 195

UnsupCasMVSNet_bld		69.21 453	69.68 442	67.82 484	79.42 460	51.15 491	67.82 499	75.79 432	54.15 477	77.47 440	85.36 395	59.26 375	70.64 482	48.46 504	79.35 510	81.66 468

blend_shiyan4		70.82 434	68.15 459	78.83 348	81.06 425	59.77 398	74.58 433	83.79 351	64.94 365	77.34 441	75.47 516	29.39 535	88.89 296	58.91 415	67.86 540	87.84 383

XFeat-NN		59.92 501	59.04 503	62.58 508	63.37 547	64.42 313	55.18 535	60.26 533	41.73 533	77.26 442	69.20 530	31.98 527	58.40 539	48.23 507	84.12 482	64.93 533

WBMVS		68.76 457	68.43 456	69.75 469	83.29 392	40.30 533	67.36 502	72.21 465	57.09 456	77.05 443	85.53 388	33.68 522	80.51 432	48.79 502	90.90 355	88.45 364

Anonymous20231206		71.38 428	71.88 411	69.88 467	86.31 315	54.37 464	70.39 484	74.62 439	52.57 488	76.73 444	88.76 318	59.94 368	72.06 474	44.35 521	93.23 273	83.23 449

CMPMVS	59.41 20	75.12 373	73.57 384	79.77 326	75.84 502	67.22 276	81.21 306	82.18 374	50.78 501	76.50 445	87.66 348	55.20 418	82.99 411	62.17 388	90.64 376	89.09 350
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		72.10 418	71.69 413	73.32 439	81.57 418	53.02 476	76.77 397	78.37 411	63.31 382	76.37 446	91.85 199	36.68 516	78.98 442	47.87 508	92.45 303	87.95 378

CVMVSNet		72.62 410	71.41 418	76.28 406	83.25 394	60.34 387	83.50 233	79.02 404	37.77 542	76.33 447	85.10 397	49.60 458	87.41 339	70.54 300	77.54 520	81.08 477

PLC	73.85 16	82.09 244	80.31 281	87.45 101	90.86 165	80.29 101	85.88 158	90.65 193	68.17 307	76.32 448	86.33 374	73.12 268	92.61 171	61.40 400	90.02 387	89.44 335
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSFormer		82.23 237	81.57 254	84.19 195	85.54 339	69.26 251	91.98 39	90.08 218	71.54 249	76.23 449	85.07 400	58.69 381	94.27 98	86.26 50	88.77 410	89.03 352

lupinMVS		76.37 356	74.46 375	82.09 268	85.54 339	69.26 251	76.79 396	80.77 392	50.68 503	76.23 449	82.82 442	58.69 381	88.94 294	69.85 307	88.77 410	88.07 371

UWE-MVS		66.43 471	65.56 477	69.05 474	84.15 369	40.98 531	73.06 460	64.71 510	54.84 472	76.18 451	79.62 480	29.21 537	80.50 433	38.54 534	89.75 391	85.66 412

PatchMatch-RL		74.48 384	73.22 392	78.27 363	87.70 261	85.26 47	75.92 414	70.09 478	64.34 372	76.09 452	81.25 462	65.87 328	78.07 450	53.86 464	83.82 484	71.48 522

thisisatest0515		73.00 406	70.52 432	80.46 312	81.45 419	59.90 396	73.16 457	74.31 443	57.86 448	76.08 453	77.78 495	37.60 515	92.12 185	65.00 360	91.45 339	89.35 337

SP-NN		76.57 349	76.54 346	76.66 398	77.40 484	75.50 164	78.02 370	78.77 407	68.60 301	75.98 454	83.71 424	55.56 414	66.71 515	82.06 115	88.74 412	87.76 385

SIFT-NN		71.05 431	69.58 443	75.45 419	80.35 445	81.93 81	74.31 436	63.57 516	61.17 422	75.98 454	81.67 458	46.63 469	65.25 525	53.44 470	89.09 405	79.18 496

MS-PatchMatch		70.93 433	70.22 436	73.06 443	81.85 410	62.50 339	73.82 446	77.90 412	52.44 489	75.92 456	81.27 461	55.67 413	81.75 420	55.37 450	77.70 518	74.94 515

CHOSEN 1792x2688		72.45 412	70.56 431	78.13 364	90.02 188	63.08 328	68.72 493	83.16 361	42.99 530	75.92 456	85.46 390	57.22 397	85.18 391	49.87 495	81.67 498	86.14 405

CR-MVSNet		74.00 391	73.04 395	76.85 396	79.58 457	62.64 336	82.58 264	76.90 425	50.50 504	75.72 458	92.38 177	48.07 462	84.07 404	68.72 325	82.91 491	83.85 437

RPMNet		78.88 311	78.28 321	80.68 307	79.58 457	62.64 336	82.58 264	94.16 33	74.80 178	75.72 458	92.59 168	48.69 459	95.56 44	73.48 260	82.91 491	83.85 437

DPM-MVS		80.10 296	79.18 305	82.88 242	90.71 169	69.74 243	78.87 358	90.84 188	60.29 433	75.64 460	85.92 382	67.28 315	93.11 156	71.24 289	91.79 328	85.77 411

test_vis1_n		70.29 438	69.99 440	71.20 460	75.97 501	66.50 289	76.69 399	80.81 391	44.22 525	75.43 461	77.23 502	50.00 455	68.59 498	66.71 342	82.85 493	78.52 503

PVSNet_BlendedMVS		78.80 313	77.84 327	81.65 281	84.43 361	63.41 323	79.49 340	90.44 201	61.70 409	75.43 461	87.07 363	69.11 306	91.44 205	60.68 404	92.24 312	90.11 319

PVSNet_Blended		76.49 353	75.40 360	79.76 327	84.43 361	63.41 323	75.14 425	90.44 201	57.36 453	75.43 461	78.30 492	69.11 306	91.44 205	60.68 404	87.70 433	84.42 427

PAPR		78.84 312	78.10 325	81.07 296	85.17 348	60.22 389	82.21 281	90.57 197	62.51 391	75.32 464	84.61 407	74.99 228	92.30 180	59.48 411	88.04 425	90.68 299

N_pmnet		70.20 439	68.80 454	74.38 429	80.91 427	84.81 52	59.12 529	76.45 430	55.06 470	75.31 465	82.36 448	55.74 412	54.82 541	47.02 511	87.24 438	83.52 442

cascas		76.29 357	74.81 371	80.72 305	84.47 360	62.94 329	73.89 445	87.34 279	55.94 462	75.16 466	76.53 508	63.97 343	91.16 221	65.00 360	90.97 353	88.06 373

SD_0403		76.08 359	76.77 343	73.98 431	87.08 290	49.45 499	83.62 225	84.68 341	63.31 382	75.13 467	87.47 353	71.85 286	84.56 396	49.97 492	87.86 429	87.94 379

SCA		73.32 399	72.57 406	75.58 418	81.62 417	55.86 448	78.89 357	71.37 473	61.73 407	74.93 468	83.42 430	60.46 363	87.01 345	58.11 423	82.63 496	83.88 434

test_vis1_n_1920		71.30 429	71.58 416	70.47 462	77.58 481	59.99 395	74.25 437	84.22 346	51.06 498	74.85 469	79.10 483	55.10 419	68.83 497	68.86 322	79.20 513	82.58 456

xiu_mvs_v2_base		77.19 338	76.75 344	78.52 354	87.01 292	61.30 367	75.55 421	87.12 291	61.24 418	74.45 470	78.79 487	77.20 197	90.93 230	64.62 367	84.80 477	83.32 447

CANet		83.79 195	82.85 223	86.63 117	86.17 321	72.21 206	83.76 220	91.43 164	77.24 145	74.39 471	87.45 354	75.36 223	95.42 55	77.03 190	92.83 286	92.25 244

PS-MVSNAJ		77.04 342	76.53 347	78.56 353	87.09 288	61.40 364	75.26 423	87.13 287	61.25 417	74.38 472	77.22 503	76.94 203	90.94 229	64.63 366	84.83 476	83.35 446

ALIKED-NN		74.80 381	73.22 392	79.55 333	82.93 401	83.79 62	81.84 287	82.56 367	47.43 512	74.33 473	88.03 333	53.21 428	76.31 458	54.08 462	94.57 215	78.54 502

MVP-Stereo		75.81 365	73.51 386	82.71 244	89.35 199	73.62 177	80.06 328	85.20 324	60.30 432	73.96 474	87.94 336	57.89 392	89.45 285	52.02 483	74.87 525	85.06 419
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WB-MVSnew		68.72 458	69.01 450	67.85 483	83.22 396	43.98 522	74.93 429	65.98 502	55.09 469	73.83 475	79.11 482	65.63 331	71.89 476	38.21 535	85.04 469	87.69 386

UGNet		82.78 226	81.64 249	86.21 130	86.20 320	76.24 153	86.86 133	85.68 316	77.07 146	73.76 476	92.82 161	69.64 301	91.82 194	69.04 319	93.69 253	90.56 305
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		74.82 380	73.74 382	78.04 367	89.57 193	60.04 391	76.49 404	87.09 292	54.31 475	73.66 477	79.80 477	60.25 366	86.76 356	58.37 419	84.15 481	87.32 390

Test_1112_low_res		73.90 392	73.08 394	76.35 404	90.35 176	55.95 445	73.40 455	86.17 304	50.70 502	73.14 478	85.94 381	58.31 383	85.90 378	56.51 437	83.22 488	87.20 392

1314		73.22 401	72.56 407	75.20 421	80.41 440	57.84 432	81.64 292	85.36 320	51.68 495	73.10 479	76.65 507	61.45 358	85.19 390	63.54 375	79.21 512	82.59 455

test_vis1_rt		65.64 477	64.09 481	70.31 463	66.09 541	70.20 237	61.16 524	81.60 383	38.65 539	72.87 480	69.66 529	52.84 432	60.04 535	56.16 439	77.77 517	80.68 481

Patchmatch-test		65.91 474	67.38 462	61.48 514	75.51 504	43.21 526	68.84 492	63.79 515	62.48 392	72.80 481	83.42 430	44.89 494	59.52 536	48.27 506	86.45 450	81.70 467

PatchmatchNet		69.71 448	68.83 453	72.33 453	77.66 480	53.60 471	79.29 348	69.99 479	57.66 450	72.53 482	82.93 439	46.45 470	80.08 436	60.91 403	72.09 531	83.31 448
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm		67.95 460	68.08 461	67.55 485	78.74 470	43.53 524	75.60 417	67.10 498	54.92 471	72.23 483	88.10 332	42.87 503	75.97 460	52.21 481	80.95 506	83.15 450

IMVS_0404		77.24 337	77.75 329	75.73 414	85.76 333	62.46 340	70.84 480	87.91 271	65.23 359	72.21 484	87.92 339	67.48 314	75.53 463	71.67 283	90.74 366	89.20 342

pmmvs5		70.73 435	70.07 437	72.72 446	77.03 489	52.73 478	74.14 440	75.65 435	50.36 505	72.17 485	85.37 394	55.42 416	80.67 430	52.86 476	87.59 435	84.77 421

PatchT		70.52 437	72.76 400	63.79 506	79.38 461	33.53 544	77.63 380	65.37 506	73.61 203	71.77 486	92.79 164	44.38 496	75.65 462	64.53 369	85.37 463	82.18 463

MVS		73.21 402	72.59 405	75.06 423	80.97 426	60.81 382	81.64 292	85.92 313	46.03 519	71.68 487	77.54 498	68.47 309	89.77 278	55.70 445	85.39 462	74.60 516

MIMVSNet		71.09 430	71.59 414	69.57 471	87.23 280	50.07 497	78.91 356	71.83 469	60.20 435	71.26 488	91.76 206	55.08 420	76.09 459	41.06 527	87.02 444	82.54 458

WTY-MVS		67.91 461	68.35 457	66.58 492	80.82 431	48.12 503	65.96 509	72.60 460	53.67 480	71.20 489	81.68 457	58.97 377	69.06 493	48.57 503	81.67 498	82.55 457

test0.0.03 1		64.66 481	64.36 480	65.57 498	75.03 509	46.89 510	64.69 513	61.58 529	62.43 399	71.18 490	77.54 498	43.41 499	68.47 501	40.75 529	82.65 494	81.35 471

CostFormer		69.98 445	68.68 455	73.87 433	77.14 487	50.72 494	79.26 349	74.51 441	51.94 494	70.97 491	84.75 405	45.16 490	87.49 335	55.16 454	79.23 511	83.40 445

Syy-MVS		69.40 451	70.03 439	67.49 486	81.72 414	38.94 535	71.00 477	61.99 522	61.38 413	70.81 492	72.36 526	61.37 359	79.30 439	64.50 370	85.18 466	84.22 430

myMVS_eth3d		64.66 481	63.89 482	66.97 490	81.72 414	37.39 538	71.00 477	61.99 522	61.38 413	70.81 492	72.36 526	20.96 550	79.30 439	49.59 496	85.18 466	84.22 430

testing91		69.94 446	68.99 451	72.80 445	83.81 378	45.89 514	71.57 474	73.64 451	68.24 306	70.77 494	77.82 494	34.37 520	84.44 399	53.64 467	87.00 445	88.07 371

GLUNet-SfM		36.71 511	36.32 514	37.87 528	23.81 554	32.04 545	38.61 542	29.05 553	18.10 546	70.60 495	50.66 543	18.79 552	40.81 549	17.68 549	59.57 543	40.74 543

testing99		69.27 452	68.15 459	72.63 447	83.29 392	45.45 516	71.15 476	71.08 474	67.34 324	70.43 496	77.77 496	32.24 526	84.35 401	53.72 465	86.33 453	88.10 370

tpmvs		70.16 440	69.56 444	71.96 455	74.71 511	48.13 502	79.63 334	75.45 437	65.02 364	70.26 497	81.88 454	45.34 487	85.68 385	58.34 420	75.39 524	82.08 465

sss		66.92 465	67.26 463	65.90 495	77.23 486	51.10 493	64.79 512	71.72 471	52.12 493	70.13 498	80.18 474	57.96 390	65.36 524	50.21 491	81.01 504	81.25 474

tpm2		68.45 459	66.83 467	73.30 441	78.93 468	48.50 501	79.76 333	71.76 470	47.50 511	69.92 499	83.60 425	42.07 504	88.40 317	48.44 505	79.51 508	83.01 452

myMVS_eth3d28		65.83 476	65.85 472	65.78 496	83.42 386	35.71 541	67.29 503	68.01 490	67.58 321	69.80 500	77.72 497	32.29 525	74.30 469	37.49 536	89.06 406	87.32 390

testing222		66.93 464	65.30 478	71.81 456	83.38 387	45.83 515	72.06 468	67.50 492	64.12 374	69.68 501	76.37 509	27.34 543	83.00 410	38.88 531	88.38 418	86.62 401

HY-MVS	64.64 18	73.03 405	72.47 408	74.71 427	83.36 389	54.19 467	82.14 284	81.96 376	56.76 460	69.57 502	86.21 378	60.03 367	84.83 394	49.58 497	82.65 494	85.11 418

dmvs_re		66.81 468	66.98 465	66.28 493	76.87 490	58.68 423	71.66 472	72.24 463	60.29 433	69.52 503	73.53 522	52.38 436	64.40 530	44.90 519	81.44 501	75.76 513

ETVMVS		64.67 480	63.34 488	68.64 478	83.44 385	41.89 528	69.56 491	61.70 527	61.33 415	68.74 504	75.76 511	28.76 538	79.35 438	34.65 539	86.16 457	84.67 423

tpm cat1		66.76 469	65.21 479	71.42 458	77.09 488	50.62 495	78.01 371	73.68 450	44.89 522	68.64 505	79.00 484	45.51 484	82.42 415	49.91 494	70.15 534	81.23 476

IB-MVS	62.13 19	71.64 424	68.97 452	79.66 330	80.80 432	62.26 350	73.94 444	76.90 425	63.27 384	68.63 506	76.79 505	33.83 521	91.84 193	59.28 414	87.26 437	84.88 420
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		80.37 286	78.41 320	86.23 127	76.75 491	73.28 182	87.18 126	77.45 417	76.24 152	68.14 507	88.93 315	65.41 332	93.85 121	69.47 311	96.12 133	91.55 273
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dtuonly		66.56 470	67.23 464	64.55 502	69.44 535	43.53 524	66.34 508	72.11 466	48.23 510	68.04 508	83.21 433	55.95 408	66.59 517	55.55 448	86.17 456	83.53 441

PVSNet	58.17 21	66.41 472	65.63 476	68.75 477	81.96 408	49.88 498	62.19 522	72.51 462	51.03 499	68.04 508	75.34 517	50.84 448	74.77 465	45.82 518	82.96 489	81.60 469

tpmrst		66.28 473	66.69 469	65.05 501	72.82 524	39.33 534	78.20 367	70.69 477	53.16 484	67.88 510	80.36 473	48.18 461	74.75 466	58.13 422	70.79 533	81.08 477

CANet_DTU		77.81 330	77.05 337	80.09 322	81.37 421	59.90 396	83.26 240	88.29 262	69.16 287	67.83 511	83.72 423	60.93 360	89.47 283	69.22 315	89.70 392	90.88 292

EPMVS		62.47 489	62.63 491	62.01 509	70.63 532	38.74 536	74.76 430	52.86 543	53.91 478	67.71 512	80.01 475	39.40 509	66.60 516	55.54 449	68.81 539	80.68 481

UBG		64.34 484	63.35 487	67.30 488	83.50 382	40.53 532	67.46 501	65.02 507	54.77 473	67.54 513	74.47 520	32.99 524	78.50 448	40.82 528	83.58 485	82.88 453

MDTV_nov1_ep13			68.29 458		78.03 474	43.87 523	74.12 441	72.22 464	52.17 490	67.02 514	85.54 387	45.36 486	80.85 429	55.73 443	84.42 479

testing11		67.38 462	65.93 471	71.73 457	83.37 388	46.60 511	70.95 479	69.40 482	62.47 395	66.14 515	76.66 506	31.22 529	84.10 403	49.10 500	84.10 483	84.49 424

pmmvs3		62.47 489	60.02 501	69.80 468	71.58 529	64.00 318	70.52 483	58.44 537	39.77 536	66.05 516	75.84 510	27.10 545	72.28 473	46.15 516	84.77 478	73.11 520

ADS-MVSNet2		65.87 475	63.64 486	72.55 449	73.16 520	56.92 441	67.10 504	74.81 438	49.74 508	66.04 517	82.97 437	46.71 467	77.26 454	42.29 524	69.96 535	83.46 443

ADS-MVSNet		61.90 492	62.19 493	61.03 515	73.16 520	36.42 540	67.10 504	61.75 525	49.74 508	66.04 517	82.97 437	46.71 467	63.21 531	42.29 524	69.96 535	83.46 443

mvsany_test1		58.48 503	56.47 510	64.50 503	65.90 543	68.21 268	56.95 534	42.11 550	38.30 540	65.69 519	77.19 504	56.96 398	59.35 537	46.16 515	58.96 544	65.93 530

dmvs_testset		60.59 500	62.54 492	54.72 524	77.26 485	27.74 549	74.05 442	61.00 531	60.48 429	65.62 520	67.03 534	55.93 409	68.23 503	32.07 543	69.46 538	68.17 527

DSMNet-mixed		60.98 498	61.61 495	59.09 521	72.88 523	45.05 519	74.70 431	46.61 548	26.20 545	65.34 521	90.32 273	55.46 415	63.12 532	41.72 526	81.30 503	69.09 526

JIA-IIPM		69.41 450	66.64 470	77.70 375	73.19 519	71.24 223	75.67 416	65.56 505	70.42 267	65.18 522	92.97 154	33.64 523	83.06 409	53.52 469	69.61 537	78.79 500

test-LLR		67.21 463	66.74 468	68.63 479	76.45 496	55.21 457	67.89 496	67.14 496	62.43 399	65.08 523	72.39 524	43.41 499	69.37 488	61.00 401	84.89 474	81.31 472

test-mter		65.00 479	63.79 484	68.63 479	76.45 496	55.21 457	67.89 496	67.14 496	50.98 500	65.08 523	72.39 524	28.27 540	69.37 488	61.00 401	84.89 474	81.31 472

PMMVS2		55.64 508	59.27 502	44.74 526	64.30 545	12.32 556	40.60 541	49.79 545	53.19 483	65.06 525	84.81 404	53.60 426	49.76 545	32.68 542	89.41 397	72.15 521

baseline2		69.77 447	66.89 466	78.41 357	79.51 459	58.09 428	76.23 409	69.57 481	57.50 452	64.82 526	77.45 500	46.02 473	88.44 315	53.08 471	77.83 516	88.70 360

gg-mvs-nofinetune		68.96 456	69.11 448	68.52 482	76.12 500	45.32 517	83.59 226	55.88 541	86.68 32	64.62 527	97.01 11	30.36 532	83.97 406	44.78 520	82.94 490	76.26 511

PAPM		71.77 421	70.06 438	76.92 392	86.39 309	53.97 468	76.62 401	86.62 299	53.44 481	63.97 528	84.73 406	57.79 393	92.34 178	39.65 530	81.33 502	84.45 426

PDCNetPlus		57.49 505	56.93 508	59.15 520	56.36 551	47.35 509	52.32 539	77.34 420	39.50 538	63.50 529	73.19 523	13.19 555	56.86 540	47.51 509	89.48 395	73.22 519

new_pmnet		55.69 507	57.66 507	49.76 525	75.47 505	30.59 547	59.56 526	51.45 544	43.62 528	62.49 530	75.48 515	40.96 507	49.15 546	37.39 537	72.52 529	69.55 525

UWE-MVS-28		58.44 504	57.71 506	60.65 516	73.58 517	31.23 546	69.68 490	48.80 546	53.12 485	61.79 531	78.83 486	30.98 530	68.40 502	21.58 546	80.99 505	82.33 462

MDTV_nov1_ep13_2view						27.60 550	70.76 482		46.47 517	61.27 532		45.20 488		49.18 499		83.75 439

dp		60.70 499	60.29 500	61.92 511	72.04 527	38.67 537	70.83 481	64.08 512	51.28 497	60.75 533	77.28 501	36.59 517	71.58 478	47.41 510	62.34 542	75.52 514

TESTMET0.1,1		61.29 495	60.32 499	64.19 504	72.06 526	51.30 489	67.89 496	62.09 521	45.27 520	60.65 534	69.01 531	27.93 541	64.74 528	56.31 438	81.65 500	76.53 510

0.4-1-1-0.1		64.02 486	60.59 497	74.31 430	73.99 512	55.62 451	67.66 500	72.78 459	55.53 467	60.35 535	58.45 539	29.26 536	86.88 350	52.84 477	74.42 526	80.42 485

PMMVS		61.65 493	60.38 498	65.47 499	65.40 544	69.26 251	63.97 518	61.73 526	36.80 544	60.11 536	68.43 532	59.42 373	66.35 518	48.97 501	78.57 515	60.81 537

PVSNet_0	51.08 22	56.10 506	54.97 511	59.48 519	75.12 508	53.28 475	55.16 536	61.89 524	44.30 524	59.16 537	62.48 537	54.22 423	65.91 521	35.40 538	47.01 545	59.25 539

MVS-HIRNet		61.16 496	62.92 490	55.87 522	79.09 465	35.34 542	71.83 469	57.98 538	46.56 516	59.05 538	91.14 232	49.95 457	76.43 457	38.74 532	71.92 532	55.84 541

E-PMN		61.59 494	61.62 494	61.49 513	66.81 539	55.40 455	53.77 537	60.34 532	66.80 332	58.90 539	65.50 535	40.48 508	66.12 519	55.72 444	86.25 454	62.95 535

GG-mvs-BLEND				67.16 489	73.36 518	46.54 513	84.15 206	55.04 542		58.64 540	61.95 538	29.93 533	83.87 407	38.71 533	76.92 522	71.07 523

EPNet_dtu		72.87 407	71.33 419	77.49 381	77.72 478	60.55 385	82.35 275	75.79 432	66.49 336	58.39 541	81.06 463	53.68 425	85.98 373	53.55 468	92.97 281	85.95 408
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		41.90 510	42.65 513	39.67 527	70.86 530	21.11 551	61.01 525	21.42 556	57.36 453	57.97 542	50.06 544	16.40 553	58.73 538	21.03 547	27.69 549	39.17 544

0.4-1-1-0.2		62.43 491	58.81 505	73.31 440	70.85 531	54.20 466	64.36 515	72.99 456	53.70 479	57.51 543	54.59 541	29.52 534	86.44 363	51.70 489	74.02 527	79.30 494

0.3-1-1-0.015		62.57 488	58.82 504	73.82 435	71.85 528	54.96 460	65.63 510	72.97 457	54.16 476	56.95 544	55.43 540	26.76 546	86.59 359	52.05 482	73.55 528	79.92 489

EMVS		61.10 497	60.81 496	61.99 510	65.96 542	55.86 448	53.10 538	58.97 536	67.06 329	56.89 545	63.33 536	40.98 506	67.03 513	54.79 458	86.18 455	63.08 534

CHOSEN 280x420		59.08 502	56.52 509	66.76 491	76.51 494	64.39 314	49.62 540	59.00 535	43.86 526	55.66 546	68.41 533	35.55 519	68.21 504	43.25 522	76.78 523	67.69 529

MVE	40.22 23	51.82 509	50.47 512	55.87 522	62.66 548	51.91 484	31.61 544	39.28 551	40.65 534	50.76 547	74.98 519	56.24 403	44.67 547	33.94 541	64.11 541	71.04 524
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
kuosan		30.83 512	32.17 515	26.83 530	53.36 552	19.02 554	57.90 532	20.44 557	38.29 541	38.01 548	37.82 546	15.18 554	33.45 550	7.74 550	20.76 550	28.03 545

DeepMVS_CX				24.13 531	32.95 553	29.49 548		21.63 555	12.07 547	37.95 549	45.07 545	30.84 531	19.21 551	17.94 548	33.06 548	23.69 546

tmp_tt		20.25 515	24.50 518	7.49 532	4.47 556	8.70 557	34.17 543	25.16 554	1.00 550	32.43 550	18.49 547	39.37 510	9.21 552	21.64 545	43.75 546	4.57 547

test_method		30.46 513	29.60 516	33.06 529	17.99 555	3.84 558	13.62 545	73.92 445	2.79 548	18.29 551	53.41 542	28.53 539	43.25 548	22.56 544	35.27 547	52.11 542

EGC-MVSNET		74.79 382	69.99 440	89.19 66	94.89 37	87.00 19	91.89 42	86.28 302	1.09 549	2.23 552	95.98 29	81.87 137	89.48 282	79.76 141	95.96 141	91.10 283

testmvs		5.91 519	7.65 522	0.72 534	1.20 557	0.37 560	59.14 528	0.67 559	0.49 552	1.11 553	2.76 551	0.94 557	0.24 554	1.02 552	1.47 551	1.55 549

test123		6.27 518	8.08 521	0.84 533	1.11 558	0.57 559	62.90 519	0.82 558	0.54 551	1.07 554	2.75 552	1.26 556	0.30 553	1.04 551	1.26 552	1.66 548

mmdepth		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

monomultidepth		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

test_blank		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

uanet_test		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

DCPMVS		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

cdsmvs_eth3d_5k		20.81 514	27.75 517	0.00 535	0.00 559	0.00 561	0.00 546	85.44 319	0.00 553	0.00 555	82.82 442	81.46 143	0.00 555	0.00 553	0.00 553	0.00 550

pcd_1.5k_mvsjas		6.41 517	8.55 520	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	76.94 203	0.00 555	0.00 553	0.00 553	0.00 550

sosnet-low-res		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

sosnet		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

uncertanet		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

Regformer		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

ab-mvs-re		6.65 516	8.87 519	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	79.80 477	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

uanet		0.00 520	0.00 523	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

WAC-MVS						37.39 538								52.61 479

MSC_two_6792asdad				88.81 72	91.55 141	77.99 126		91.01 182					96.05 8	87.45 28	98.17 36	92.40 229

No_MVS				88.81 72	91.55 141	77.99 126		91.01 182					96.05 8	87.45 28	98.17 36	92.40 229

eth-test2					0.00 559

eth-test					0.00 559

OPU-MVS				88.27 88	91.89 125	77.83 129	90.47 60				91.22 228	81.12 147	94.68 83	74.48 230	95.35 171	92.29 240

save fliter					93.75 67	77.44 136	86.31 148	89.72 228	70.80 263

test_0728_SECOND				86.79 114	94.25 52	72.45 201	90.54 57	94.10 40					95.88 18	86.42 46	97.97 48	92.02 255

GSMVS																83.88 434

sam_mvs1												46.11 472				83.88 434

sam_mvs												45.92 478

MTGPA								91.81 154

test_post1							78.85 359				3.13 549	45.19 489	80.13 435	58.11 423

test_post											3.10 550	45.43 485	77.22 455

patchmatchnet-post											81.71 456	45.93 477	87.01 345

MTMP							90.66 53	33.14 552

gm-plane-assit					75.42 506	44.97 520			52.17 490		72.36 526		87.90 327	54.10 461

test9_res														80.83 130	96.45 117	90.57 304

agg_prior2														79.68 143	96.16 130	90.22 313

test_prior4						78.97 115	84.59 193

test_prior				86.32 124	90.59 172	71.99 209		92.85 114					94.17 108			92.80 202

新几何2							81.72 291

旧先验1					91.97 121	71.77 211		81.78 379			91.84 200	73.92 251			93.65 254	83.61 440

无先验							82.81 259	85.62 317	58.09 446				91.41 208	67.95 333		84.48 425

原ACMM2							82.26 280

testdata2													86.43 364	63.52 377

segment_acmp												81.94 133

testdata1							79.62 335		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 63	80.78 131	95.83 152	94.46 104

plane_prior4											92.95 155

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								0.00 560

nn								0.00 560

door-mid								74.45 442

test11								91.46 163

door								72.57 461

HQP5-MVS						70.66 229

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					90.17 282

ACMMP++_ref															95.74 159

ACMMP++															97.35 84

Test By Simon												79.09 168

High-resolution multi-view benchmark