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		86.90 1	88.67 1	81.57 24	91.50 1	63.30 161	84.80 39	87.77 10	86.18 1	96.26 1	96.06 1	90.32 1	84.49 77	68.08 117	97.05 1	96.93 1

UA-Net		81.56 39	82.28 47	79.40 51	88.91 28	69.16 90	84.67 40	80.01 172	75.34 18	79.80 137	94.91 2	69.79 104	80.25 163	72.63 79	94.46 40	88.78 44

UniMVSNet_ETH3D		76.74 88	79.02 68	69.92 241	89.27 19	43.81 393	74.47 170	71.70 295	72.33 43	85.50 61	93.65 3	77.98 24	76.88 233	54.60 292	91.64 98	89.08 34

tt0320		71.34 192	73.47 144	64.97 331	79.92 154	40.81 424	65.22 355	69.07 336	66.72 78	76.15 223	93.36 4	70.35 94	66.90 384	49.31 341	91.09 119	87.21 63

OurMVSNet-221017-0		78.57 69	78.53 75	78.67 63	80.48 146	64.16 150	80.24 85	82.06 121	61.89 132	88.77 15	93.32 5	57.15 271	82.60 113	70.08 100	92.80 80	89.25 30

tt0320-xc		71.50 187	73.63 140	65.08 329	79.77 156	40.46 433	64.80 363	68.86 342	67.08 73	76.84 199	93.24 6	70.33 95	66.77 391	49.76 333	92.02 94	88.02 53

K. test v3		73.67 126	73.61 141	73.87 136	79.78 155	55.62 249	74.69 166	62.04 403	66.16 84	84.76 73	93.23 7	49.47 331	80.97 149	65.66 146	86.67 241	85.02 126

LTVRE_ROB	75.46 1	84.22 9	84.98 11	81.94 23	84.82 80	75.40 36	91.60 3	87.80 8	73.52 28	88.90 14	93.06 8	71.39 85	81.53 135	81.53 4	92.15 93	88.91 40
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
DTE-MVSNet		80.35 55	82.89 40	72.74 174	89.84 7	37.34 466	77.16 123	81.81 126	80.45 3	90.92 3	92.95 9	74.57 55	86.12 33	63.65 171	94.68 36	94.76 6

Anonymous20231211		75.54 99	77.19 89	70.59 213	77.67 196	45.70 372	74.73 164	80.19 167	68.80 62	82.95 94	92.91 10	66.26 146	76.76 236	58.41 242	92.77 81	89.30 27

PEN-MVS		80.46 53	82.91 39	73.11 154	89.83 8	39.02 446	77.06 126	82.61 108	80.04 4	90.60 6	92.85 11	74.93 51	85.21 65	63.15 178	95.15 22	95.09 2

pmmvs6		71.82 181	73.66 138	66.31 316	75.94 236	42.01 410	66.99 325	72.53 287	63.45 118	76.43 217	92.78 12	72.95 68	69.69 351	51.41 319	90.46 138	87.22 62

PS-CasMVS		80.41 54	82.86 41	73.07 156	89.93 6	39.21 442	77.15 124	81.28 139	79.74 5	90.87 4	92.73 13	75.03 50	84.93 70	63.83 168	95.19 20	95.07 3

gg-mvs-nofinetune		55.75 427	56.75 415	52.72 463	62.87 468	28.04 520	68.92 279	41.36 530	71.09 50	50.80 519	92.63 14	20.74 528	66.86 388	29.97 510	72.41 470	63.25 495

TDRefinement		86.32 2	86.33 2	86.29 1	88.64 31	81.19 5	88.84 4	90.72 1	78.27 11	87.95 18	92.53 15	79.37 15	84.79 74	74.51 59	96.15 2	92.88 7

v7n		79.37 63	80.41 59	76.28 100	78.67 181	55.81 245	79.22 98	82.51 112	70.72 53	87.54 26	92.44 16	68.00 124	81.34 137	72.84 77	91.72 96	91.69 10

PS-MVSNAJss		77.54 79	77.35 88	78.13 76	84.88 79	66.37 122	78.55 104	79.59 184	53.48 252	86.29 45	92.43 17	62.39 188	80.25 163	67.90 122	90.61 135	87.77 55

test_djsdf		78.88 66	78.27 77	80.70 38	81.42 135	71.24 65	83.98 45	75.72 249	52.27 267	87.37 31	92.25 18	68.04 123	80.56 156	72.28 84	91.15 114	90.32 20

SixPastTwentyTwo		75.77 94	76.34 95	74.06 132	81.69 132	54.84 256	76.47 131	75.49 251	64.10 109	87.73 22	92.24 19	50.45 324	81.30 139	67.41 127	91.46 104	86.04 94

reproduce_model		84.87 5	85.80 5	82.05 22	85.52 68	78.14 16	87.69 6	85.36 39	79.26 6	89.12 11	92.10 20	77.52 26	85.92 41	80.47 8	95.20 19	82.10 237

WR-MVS_H		80.22 57	82.17 48	74.39 126	89.46 14	42.69 406	78.24 109	82.24 118	78.21 12	89.57 9	92.10 20	68.05 122	85.59 54	66.04 142	95.62 9	94.88 5

PMVS	70.70 6	81.70 38	83.15 36	77.36 87	90.35 5	82.82 2	82.15 64	79.22 192	74.08 23	87.16 34	91.97 22	84.80 2	76.97 229	64.98 150	93.61 70	72.28 409
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
lecture		83.41 20	85.02 10	78.58 65	83.87 98	67.26 108	84.47 41	88.27 6	73.64 27	87.35 32	91.96 23	78.55 21	82.92 106	81.59 3	95.50 10	85.56 108

MVSMamba_PlusPlus		76.88 86	78.21 78	72.88 168	80.83 142	48.71 311	83.28 57	82.79 102	72.78 31	79.17 146	91.94 24	56.47 281	83.95 83	70.51 98	86.15 245	85.99 96

ANet_high		67.08 282	69.94 221	58.51 427	57.55 511	27.09 524	58.43 448	76.80 235	63.56 115	82.40 102	91.93 25	59.82 230	64.98 406	50.10 331	88.86 185	83.46 187

reproduce-ours		84.97 3	85.93 3	82.10 20	86.11 59	77.53 21	87.08 13	85.81 29	78.70 9	88.94 12	91.88 26	79.74 12	86.05 34	79.90 9	95.21 17	82.72 219

our_new_method		84.97 3	85.93 3	82.10 20	86.11 59	77.53 21	87.08 13	85.81 29	78.70 9	88.94 12	91.88 26	79.74 12	86.05 34	79.90 9	95.21 17	82.72 219

mvs_tets		78.93 65	78.67 72	79.72 46	84.81 81	73.93 48	80.65 77	76.50 237	51.98 275	87.40 28	91.86 28	76.09 39	78.53 190	68.58 112	90.20 143	86.69 75

sc_t1		72.50 168	74.23 126	67.33 296	80.05 152	46.99 350	66.58 333	69.48 328	66.28 82	77.62 177	91.83 29	70.98 90	68.62 364	53.86 304	91.40 105	86.37 86

test_0402		78.17 75	79.48 66	74.24 128	83.50 101	59.15 209	72.52 198	74.60 260	75.34 18	88.69 17	91.81 30	75.06 49	82.37 119	65.10 148	88.68 186	81.20 257

APDe-MVS		82.88 27	84.14 18	79.08 55	84.80 82	66.72 117	86.54 23	85.11 43	72.00 45	86.65 39	91.75 31	78.20 23	87.04 10	77.93 30	94.32 52	83.47 186
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
VDDNet		71.60 185	73.13 154	67.02 305	86.29 47	41.11 419	69.97 254	66.50 363	68.72 64	74.74 256	91.70 32	59.90 228	75.81 245	48.58 351	91.72 96	84.15 165

CP-MVSNet		79.48 61	81.65 52	72.98 160	89.66 12	39.06 445	76.76 127	80.46 162	78.91 8	90.32 7	91.70 32	68.49 115	84.89 71	63.40 175	95.12 23	95.01 4

HPM-MVS_fast		84.59 7	85.10 9	83.06 4	88.60 32	75.83 33	86.27 27	86.89 16	73.69 26	86.17 46	91.70 32	78.23 22	85.20 66	79.45 16	94.91 29	88.15 52

EGC-MVSNET		64.77 317	61.17 368	75.60 111	86.90 42	74.47 43	84.04 44	68.62 349	0.60 549	1.13 552	91.61 35	65.32 159	74.15 278	64.01 162	88.28 192	78.17 321

jajsoiax		78.51 70	78.16 79	79.59 48	84.65 84	73.83 50	80.42 80	76.12 244	51.33 286	87.19 33	91.51 36	73.79 62	78.44 195	68.27 115	90.13 147	86.49 83

SMA-MVS		82.12 33	82.68 44	80.43 39	88.90 29	69.52 82	85.12 36	84.76 54	63.53 116	84.23 80	91.47 37	72.02 74	87.16 7	79.74 13	94.36 49	84.61 145
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
COLMAP_ROB	72.78 3	83.75 14	84.11 19	82.68 12	82.97 113	74.39 45	87.18 11	88.18 7	78.98 7	86.11 49	91.47 37	79.70 14	85.76 48	66.91 137	95.46 13	87.89 54
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TSAR-MVS + MP.		79.05 64	78.81 69	79.74 45	88.94 27	67.52 105	86.61 22	81.38 137	51.71 277	77.15 189	91.42 39	65.49 156	87.20 6	79.44 17	87.17 231	84.51 154
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MP-MVS-pluss		82.54 30	83.46 30	79.76 44	88.88 30	68.44 96	81.57 69	86.33 19	63.17 122	85.38 64	91.26 40	76.33 36	84.67 76	83.30 1	94.96 27	86.17 91
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
LPG-MVS_test		83.47 19	84.33 16	80.90 35	87.00 39	70.41 75	82.04 66	86.35 17	69.77 59	87.75 20	91.13 41	81.83 3	86.20 28	77.13 40	95.96 5	86.08 92

LGP-MVS_train				80.90 35	87.00 39	70.41 75		86.35 17	69.77 59	87.75 20	91.13 41	81.83 3	86.20 28	77.13 40	95.96 5	86.08 92

ACMH+	66.64 10	81.20 43	82.48 45	77.35 88	81.16 140	62.39 167	80.51 78	87.80 8	73.02 30	87.57 25	91.08 43	80.28 9	82.44 116	64.82 152	96.10 4	87.21 63

ACMMP_NAP		82.33 32	83.28 33	79.46 50	89.28 18	69.09 93	83.62 51	84.98 48	64.77 104	83.97 83	91.02 44	75.53 45	85.93 40	82.00 2	94.36 49	83.35 194

MP-MVS		83.19 22	83.54 28	82.14 19	90.54 4	79.00 12	86.42 25	83.59 87	71.31 47	81.26 120	90.96 45	74.57 55	84.69 75	78.41 25	94.78 32	82.74 218
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testf1		75.66 97	76.57 92	72.95 161	67.07 418	67.62 103	76.10 143	80.68 155	64.95 100	86.58 41	90.94 46	71.20 87	71.68 322	60.46 208	91.13 116	79.56 294

APD_test2		75.66 97	76.57 92	72.95 161	67.07 418	67.62 103	76.10 143	80.68 155	64.95 100	86.58 41	90.94 46	71.20 87	71.68 322	60.46 208	91.13 116	79.56 294

anonymousdsp		78.60 68	77.80 81	81.00 34	78.01 190	74.34 46	80.09 87	76.12 244	50.51 302	89.19 10	90.88 48	71.45 83	77.78 213	73.38 71	90.60 136	90.90 16

PGM-MVS		83.07 25	83.25 35	82.54 15	89.57 13	77.21 28	82.04 66	85.40 37	67.96 68	84.91 71	90.88 48	75.59 42	86.57 15	78.16 27	94.71 35	83.82 172

mPP-MVS		84.01 13	84.39 15	82.88 6	90.65 3	81.38 4	87.08 13	82.79 102	72.41 41	85.11 67	90.85 50	76.65 33	84.89 71	79.30 20	94.63 37	82.35 230

MTAPA		83.19 22	83.87 23	81.13 33	91.16 2	78.16 15	84.87 37	80.63 158	72.08 44	84.93 68	90.79 51	74.65 54	84.42 80	80.98 5	94.75 33	80.82 269

MIMVSNet1		66.57 291	69.23 239	58.59 426	81.26 139	37.73 462	64.06 378	57.62 428	57.02 182	78.40 160	90.75 52	62.65 182	58.10 445	41.77 412	89.58 163	79.95 289

SR-MVS-dyc-post		84.75 6	85.26 8	83.21 3	86.19 52	79.18 10	87.23 9	86.27 20	77.51 13	87.65 23	90.73 53	79.20 16	85.58 55	78.11 28	94.46 40	84.89 127

RE-MVS-def			85.50 6		86.19 52	79.18 10	87.23 9	86.27 20	77.51 13	87.65 23	90.73 53	81.38 7		78.11 28	94.46 40	84.89 127

region2R		83.54 17	83.86 24	82.58 14	89.82 9	77.53 21	87.06 16	84.23 77	70.19 57	83.86 85	90.72 55	75.20 47	86.27 25	79.41 18	94.25 54	83.95 169

ACMMPR		83.62 15	83.93 21	82.69 11	89.78 10	77.51 25	87.01 17	84.19 78	70.23 55	84.49 76	90.67 56	75.15 48	86.37 19	79.58 14	94.26 53	84.18 163

ACMMP		84.22 9	84.84 12	82.35 17	89.23 21	76.66 31	87.65 7	85.89 27	71.03 51	85.85 51	90.58 57	78.77 18	85.78 47	79.37 19	95.17 21	84.62 144
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
CP-MVS		84.12 11	84.55 14	82.80 10	89.42 17	79.74 9	88.19 5	84.43 68	71.96 46	84.70 74	90.56 58	77.12 29	86.18 30	79.24 21	95.36 14	82.49 227

Baseline_NR-MVSNet		70.62 207	73.19 152	62.92 365	76.97 211	34.44 487	68.84 281	70.88 316	60.25 146	79.50 142	90.53 59	61.82 198	69.11 358	54.67 291	95.27 15	85.22 115

DeepC-MVS	72.44 4	81.00 47	80.83 57	81.50 25	86.70 44	70.03 79	82.06 65	87.00 15	59.89 149	80.91 126	90.53 59	72.19 71	88.56 1	73.67 70	94.52 39	85.92 98
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APD-MVS_3200maxsize		83.57 16	84.33 16	81.31 31	82.83 116	73.53 53	85.50 34	87.45 13	74.11 22	86.45 43	90.52 61	80.02 10	84.48 78	77.73 32	94.34 51	85.93 97

Anonymous20240529		72.56 164	73.79 136	68.86 268	76.89 219	45.21 376	68.80 287	77.25 228	67.16 72	76.89 195	90.44 62	65.95 150	74.19 277	50.75 324	90.00 150	87.18 66

HFP-MVS		83.39 21	84.03 20	81.48 26	89.25 20	75.69 35	87.01 17	84.27 74	70.23 55	84.47 77	90.43 63	76.79 30	85.94 38	79.58 14	94.23 55	82.82 215

HPM-MVS		84.12 11	84.63 13	82.60 13	88.21 35	74.40 44	85.24 35	87.21 14	70.69 54	85.14 66	90.42 64	78.99 17	86.62 14	80.83 6	94.93 28	86.79 72
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DVP-MVS		81.15 44	83.12 37	75.24 118	86.16 54	60.78 189	83.77 49	80.58 160	72.48 37	85.83 52	90.41 65	78.57 19	85.69 50	75.86 43	94.39 45	79.24 301
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									74.03 24	85.83 52	90.41 65	75.58 43	85.69 50	77.43 35	94.74 34	84.31 160

SteuartSystems-ACMMP		83.07 25	83.64 27	81.35 29	85.14 75	71.00 68	85.53 33	84.78 53	70.91 52	85.64 54	90.41 65	75.55 44	87.69 4	79.75 11	95.08 24	85.36 113
Skip Steuart: Steuart Systems R&D Blog.
ZNCC-MVS		83.12 24	83.68 26	81.45 27	89.14 24	73.28 55	86.32 26	85.97 25	67.39 71	84.02 82	90.39 68	74.73 53	86.46 16	80.73 7	94.43 44	84.60 147

XVS		83.51 18	83.73 25	82.85 8	89.43 15	77.61 19	86.80 20	84.66 60	72.71 32	82.87 95	90.39 68	73.86 60	86.31 22	78.84 23	94.03 60	84.64 142

DVP-MVS++		81.24 42	82.74 43	76.76 92	83.14 106	60.90 187	91.64 1	85.49 33	74.03 24	84.93 68	90.38 70	66.82 137	85.90 42	77.43 35	90.78 131	83.49 183

test_one_0601					85.84 66	61.45 177		85.63 31	75.27 20	85.62 57	90.38 70	76.72 32

FC-MVSNet-test		73.32 139	74.78 112	68.93 266	79.21 166	36.57 469	71.82 223	79.54 186	57.63 176	82.57 101	90.38 70	59.38 238	78.99 182	57.91 247	94.56 38	91.23 12

GBi-Net		68.30 257	68.79 245	66.81 307	73.14 297	40.68 427	71.96 212	73.03 274	54.81 214	74.72 257	90.36 73	48.63 343	75.20 258	47.12 364	85.37 258	84.54 150

test1		68.30 257	68.79 245	66.81 307	73.14 297	40.68 427	71.96 212	73.03 274	54.81 214	74.72 257	90.36 73	48.63 343	75.20 258	47.12 364	85.37 258	84.54 150

FMVSNet1		71.06 196	72.48 172	66.81 307	77.65 197	40.68 427	71.96 212	73.03 274	61.14 137	79.45 143	90.36 73	60.44 220	75.20 258	50.20 330	88.05 198	84.54 150

SR-MVS		84.51 8	85.27 7	82.25 18	88.52 33	77.71 18	86.81 19	85.25 41	77.42 16	86.15 47	90.24 76	81.69 5	85.94 38	77.77 31	93.58 71	83.09 203

ACMH	63.62 14	77.50 82	80.11 61	69.68 245	79.61 158	56.28 239	78.81 101	83.62 86	63.41 120	87.14 35	90.23 77	76.11 38	73.32 287	67.58 124	94.44 43	79.44 298
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GST-MVS		82.79 28	83.27 34	81.34 30	88.99 26	73.29 54	85.94 32	85.13 42	68.58 66	84.14 81	90.21 78	73.37 64	86.41 17	79.09 22	93.98 63	84.30 162

3Dnovator+	73.19 2	81.08 46	80.48 58	82.87 7	81.41 136	72.03 58	84.38 43	86.23 23	77.28 17	80.65 129	90.18 79	59.80 231	87.58 5	73.06 74	91.34 107	89.01 36

MED-MVS		81.77 37	82.86 41	78.51 67	86.27 48	64.31 146	86.10 28	84.54 64	72.46 39	85.54 58	90.03 80	72.97 67	86.37 19	74.09 63	93.74 67	84.86 130

TestfortrainingZip a		82.48 31	83.93 21	78.11 77	86.27 48	64.11 152	86.10 28	85.02 46	72.46 39	86.32 44	90.03 80	76.75 31	85.37 57	78.23 26	94.22 56	84.86 130

DPE-MVS		82.00 35	83.02 38	78.95 60	85.36 71	67.25 109	82.91 59	84.98 48	73.52 28	85.43 62	90.03 80	76.37 35	86.97 12	74.56 57	94.02 62	82.62 223
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ACMP	69.50 8	82.64 29	83.38 31	80.40 40	86.50 45	69.44 84	82.30 63	86.08 24	66.80 76	86.70 38	89.99 83	81.64 6	85.95 37	74.35 61	96.11 3	85.81 99
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test0726					86.16 54	60.78 189	83.81 48	85.10 44	72.48 37	85.27 65	89.96 84	78.57 19

LS3D		80.99 48	80.85 56	81.41 28	78.37 182	71.37 63	87.45 8	85.87 28	77.48 15	81.98 106	89.95 85	69.14 107	85.26 62	66.15 139	91.24 110	87.61 58

TransMVSNet (Re)		69.62 228	71.63 192	63.57 349	76.51 225	35.93 477	65.75 346	71.29 307	61.05 138	75.02 250	89.90 86	65.88 152	70.41 340	49.79 332	89.48 165	84.38 158

RPSCF		75.76 95	74.37 122	79.93 43	74.81 253	77.53 21	77.53 118	79.30 189	59.44 152	78.88 149	89.80 87	71.26 86	73.09 290	57.45 252	80.89 366	89.17 33

SED-MVS		81.78 36	83.48 29	76.67 93	86.12 56	61.06 183	83.62 51	84.72 56	72.61 35	87.38 29	89.70 88	77.48 27	85.89 44	75.29 47	94.39 45	83.08 204

test_241102_TWO								84.80 51	72.61 35	84.93 68	89.70 88	77.73 25	85.89 44	75.29 47	94.22 56	83.25 196

XVG-ACMP-BASELINE		80.54 51	81.06 55	78.98 59	87.01 38	72.91 56	80.23 86	85.56 32	66.56 80	85.64 54	89.57 90	69.12 108	80.55 158	72.51 81	93.37 73	83.48 185

test_241102_ONE					86.12 56	61.06 183		84.72 56	72.64 34	87.38 29	89.47 91	77.48 27	85.74 49

FIs		72.56 164	73.80 135	68.84 269	78.74 180	37.74 461	71.02 237	79.83 175	56.12 195	80.88 128	89.45 92	58.18 254	78.28 202	56.63 261	93.36 74	90.51 19

pm-mvs1		68.40 255	69.85 224	64.04 341	73.10 300	39.94 437	64.61 369	70.50 319	55.52 207	73.97 281	89.33 93	63.91 173	68.38 366	49.68 335	88.02 199	83.81 174

OPM-MVS		80.99 48	81.63 53	79.07 56	86.86 43	69.39 85	79.41 96	84.00 83	65.64 86	85.54 58	89.28 94	76.32 37	83.47 96	74.03 67	93.57 72	84.35 159
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v8		75.07 107	75.64 103	73.35 146	73.42 291	47.46 339	75.20 154	81.45 134	60.05 147	85.64 54	89.26 95	58.08 260	81.80 132	69.71 106	87.97 201	90.79 17

TranMVSNet+NR-MVSNet		76.13 92	77.66 83	71.56 197	84.61 85	42.57 408	70.98 238	78.29 212	68.67 65	83.04 91	89.26 95	72.99 66	80.75 154	55.58 278	95.47 12	91.35 11

SSC-MVS		61.79 364	66.08 297	48.89 488	76.91 216	10.00 554	53.56 482	47.37 495	68.20 67	76.56 210	89.21 97	54.13 297	57.59 447	54.75 289	74.07 458	79.08 304

nrg030		74.87 114	75.99 100	71.52 198	74.90 249	49.88 303	74.10 177	82.58 109	54.55 224	83.50 89	89.21 97	71.51 81	75.74 248	61.24 198	92.34 89	88.94 39

SF-MVS		80.72 50	81.80 49	77.48 84	82.03 127	64.40 144	83.41 55	88.46 5	65.28 94	84.29 79	89.18 99	73.73 63	83.22 100	76.01 42	93.77 65	84.81 136

v10		75.69 96	76.20 97	74.16 130	74.44 267	48.69 312	75.84 149	82.93 100	59.02 157	85.92 50	89.17 100	58.56 251	82.74 111	70.73 94	89.14 176	91.05 13

ACMM	69.25 9	82.11 34	83.31 32	78.49 68	88.17 36	73.96 47	83.11 58	84.52 66	66.40 81	87.45 27	89.16 101	81.02 8	80.52 159	74.27 62	95.73 7	80.98 265
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ZD-MVS					83.91 95	69.36 86		81.09 146	58.91 159	82.73 99	89.11 102	75.77 41	86.63 13	72.73 78	92.93 79

HQP_MVS		78.77 67	78.78 71	78.72 62	85.18 72	65.18 136	82.74 61	85.49 33	65.45 89	78.23 163	89.11 102	60.83 214	86.15 31	71.09 90	90.94 123	84.82 134

plane_prior4											89.11 102

mvs5depth		66.35 295	67.98 263	61.47 386	62.43 474	51.05 284	69.38 266	69.24 331	56.74 188	73.62 287	89.06 105	46.96 353	58.63 438	55.87 272	88.49 189	74.73 376

lessismore_v0				72.75 173	79.60 159	56.83 238		57.37 432		83.80 86	89.01 106	47.45 351	78.74 187	64.39 159	86.49 244	82.69 221

XVG-OURS		79.51 60	79.82 63	78.58 65	86.11 59	74.96 40	76.33 140	84.95 50	66.89 74	82.75 98	88.99 107	66.82 137	78.37 199	74.80 50	90.76 134	82.40 229

APD-MVS		81.13 45	81.73 51	79.36 52	84.47 87	70.53 74	83.85 47	83.70 85	69.43 61	83.67 87	88.96 108	75.89 40	86.41 17	72.62 80	92.95 78	81.14 259
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Gipuma		69.55 230	72.83 163	59.70 411	63.63 465	53.97 263	80.08 88	75.93 247	64.24 108	73.49 292	88.93 109	57.89 264	62.46 415	59.75 224	91.55 102	62.67 498
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
Casviewmamba		77.76 77	78.57 74	75.31 115	76.72 221	53.06 270	76.28 141	85.90 26	62.98 125	81.96 107	88.90 110	75.35 46	82.88 108	68.97 109	90.11 148	89.98 21

XVG-OURS-SEG-HR		79.62 59	79.99 62	78.49 68	86.46 46	74.79 41	77.15 124	85.39 38	66.73 77	80.39 133	88.85 111	74.43 58	78.33 201	74.73 52	85.79 252	82.35 230

casdiffmvs_mvg		75.26 103	76.18 98	72.52 180	72.87 309	49.47 305	72.94 195	84.71 58	59.49 151	80.90 127	88.81 112	70.07 99	79.71 171	67.40 128	88.39 191	88.40 49
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MM		78.15 76	77.68 82	79.55 49	80.10 151	65.47 132	80.94 74	78.74 202	71.22 49	72.40 315	88.70 113	60.51 218	87.70 3	77.40 37	89.13 177	85.48 110

VDD-MVS		70.81 204	71.44 198	68.91 267	79.07 173	46.51 360	67.82 306	70.83 317	61.23 136	74.07 277	88.69 114	59.86 229	75.62 250	51.11 321	90.28 142	84.61 145

test2506		61.23 371	60.85 374	62.38 371	78.80 178	27.88 521	67.33 316	37.42 540	54.23 233	67.55 400	88.68 115	17.87 543	74.39 273	46.33 374	89.41 167	84.86 130

ECVR-MVS		64.82 315	65.22 311	63.60 348	78.80 178	31.14 506	66.97 326	56.47 443	54.23 233	69.94 362	88.68 115	37.23 427	74.81 266	45.28 386	89.41 167	84.86 130

mmtdpeth		68.76 247	70.55 215	63.40 356	67.06 421	56.26 240	68.73 291	71.22 311	55.47 208	70.09 358	88.64 117	65.29 160	56.89 450	58.94 233	89.50 164	77.04 347

APD_test1		75.04 108	75.38 107	74.02 133	69.89 366	70.15 77	76.46 132	79.71 178	65.50 88	82.99 93	88.60 118	66.94 134	72.35 303	59.77 222	88.54 188	79.56 294

CPTT-MVS		81.51 40	81.76 50	80.76 37	89.20 22	78.75 13	86.48 24	82.03 122	68.80 62	80.92 125	88.52 119	72.00 75	82.39 118	74.80 50	93.04 77	81.14 259

test1111		64.62 319	65.19 312	62.93 364	79.01 174	29.91 513	65.45 351	54.41 454	54.09 238	71.47 341	88.48 120	37.02 428	74.29 276	46.83 369	89.94 154	84.58 148

Vis-MVSNet		74.85 115	74.56 115	75.72 108	81.63 133	64.64 142	76.35 138	79.06 194	62.85 126	73.33 295	88.41 121	62.54 186	79.59 174	63.94 167	82.92 320	82.94 208
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
HPM-MVS++		79.89 58	79.80 64	80.18 42	89.02 25	78.44 14	83.49 54	80.18 168	64.71 105	78.11 166	88.39 122	65.46 157	83.14 101	77.64 34	91.20 112	78.94 307

aaatest				78.47 70	86.27 48	64.31 146	86.10 28	84.54 64	64.93 103	85.54 58	88.38 123		86.37 19	74.09 63	94.20 58	84.73 138

aaEdge-Enhanced		81.36 41	82.39 46	78.28 73	84.42 90	64.31 146	82.78 60	85.02 46	71.25 48	84.81 72	88.38 123	76.53 34	85.81 46	74.09 63	94.20 58	84.73 138

MSP-MVS		80.49 52	79.67 65	82.96 5	89.70 11	77.46 27	87.16 12	85.10 44	64.94 102	81.05 123	88.38 123	57.10 273	87.10 8	79.75 11	83.87 302	84.31 160
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
VPA-MVSNet		68.71 249	70.37 217	63.72 347	76.13 231	38.06 457	64.10 377	71.48 301	56.60 192	74.10 275	88.31 126	64.78 166	69.72 350	47.69 362	90.15 145	83.37 193

ambc				70.10 235	77.74 194	50.21 293	74.28 175	77.93 219		79.26 144	88.29 127	54.11 298	79.77 170	64.43 158	91.10 118	80.30 284

9.14			80.22 60		80.68 144		80.35 83	87.69 11	59.90 148	83.00 92	88.20 128	74.57 55	81.75 133	73.75 69	93.78 64

AllTest		77.66 78	77.43 84	78.35 71	79.19 168	70.81 70	78.60 103	88.64 3	65.37 92	80.09 135	88.17 129	70.33 95	78.43 196	55.60 275	90.90 127	85.81 99

TestCases				78.35 71	79.19 168	70.81 70		88.64 3	65.37 92	80.09 135	88.17 129	70.33 95	78.43 196	55.60 275	90.90 127	85.81 99

LCM-MVSNet-Re		69.10 241	71.57 196	61.70 381	70.37 356	34.30 489	61.45 406	79.62 181	56.81 186	89.59 8	88.16 131	68.44 116	72.94 291	42.30 404	87.33 216	77.85 328

MG-MVS		70.47 210	71.34 199	67.85 285	79.26 164	40.42 434	74.67 167	75.15 255	58.41 164	68.74 387	88.14 132	56.08 284	83.69 90	59.90 219	81.71 346	79.43 299

hybridcas		73.97 122	75.17 108	70.38 217	73.56 286	47.22 344	72.99 194	82.30 116	56.94 183	79.54 140	88.05 133	72.64 69	76.88 233	63.11 179	87.43 211	87.04 69

IS-MVSNet		75.10 106	75.42 106	74.15 131	79.23 165	48.05 325	79.43 94	78.04 216	70.09 58	79.17 146	88.02 134	53.04 303	83.60 91	58.05 246	93.76 66	90.79 17

Elysia		77.52 80	77.43 84	77.78 80	79.01 174	60.26 195	76.55 129	84.34 70	67.82 69	78.73 152	87.94 135	58.68 249	83.79 86	74.70 54	89.10 179	89.28 28

StellarMVS		77.52 80	77.43 84	77.78 80	79.01 174	60.26 195	76.55 129	84.34 70	67.82 69	78.73 152	87.94 135	58.68 249	83.79 86	74.70 54	89.10 179	89.28 28

tt0805		76.12 93	78.43 76	69.20 255	81.32 137	41.37 416	76.72 128	77.64 221	63.78 113	82.06 105	87.88 137	79.78 11	79.05 180	64.33 160	92.40 87	87.17 67

tfpnnormal		66.48 292	67.93 264	62.16 374	73.40 292	36.65 468	63.45 385	64.99 377	55.97 201	72.82 307	87.80 138	57.06 274	69.10 359	48.31 355	87.54 206	80.72 274

casdiffseed414692147		74.13 119	74.76 113	72.25 189	73.89 283	49.89 302	75.54 151	82.35 115	58.57 163	77.77 171	87.76 139	69.09 109	78.46 193	59.77 222	88.10 197	88.41 48

FE-MVSNET2		68.70 250	69.85 224	65.22 326	74.82 252	37.95 459	67.28 320	73.47 270	53.40 253	77.65 176	87.72 140	59.72 232	73.17 289	46.39 372	88.23 193	84.56 149

BridgeMVS		73.59 129	74.06 130	72.17 191	77.48 200	47.72 333	81.43 71	82.20 119	54.38 228	79.19 145	87.68 141	54.41 295	83.57 92	63.98 164	85.78 253	85.22 115

PRO-TEST		72.30 171	71.12 203	75.85 107	77.17 203	57.42 233	75.49 152	81.54 130	52.02 274	78.36 161	87.56 142	50.67 322	86.31 22	56.57 262	80.71 373	83.82 172

WB-MVS		60.04 385	64.19 328	47.59 491	76.09 232	10.22 553	52.44 490	46.74 497	65.17 97	74.07 277	87.48 143	53.48 300	55.28 455	49.36 339	72.84 467	77.28 334

RRT-MVS		70.33 211	70.73 212	69.14 258	71.93 325	45.24 375	75.10 155	75.08 257	60.85 142	78.62 154	87.36 144	49.54 330	78.64 188	60.16 213	77.90 422	83.55 181

MGCNet		75.45 100	74.66 114	77.83 79	75.58 241	61.53 175	78.29 107	77.18 230	63.15 124	69.97 361	87.20 145	57.54 267	87.05 9	74.05 66	88.96 182	84.89 127

CDPH-MVS		77.33 83	77.06 91	78.14 75	84.21 92	63.98 154	76.07 145	83.45 88	54.20 235	77.68 175	87.18 146	69.98 100	85.37 57	68.01 119	92.72 83	85.08 123

casdiffmvs		73.06 146	73.84 134	70.72 211	71.32 334	46.71 355	70.93 239	84.26 75	55.62 205	77.46 181	87.10 147	67.09 133	77.81 211	63.95 165	86.83 237	87.64 57
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DU-MVS		74.91 111	75.57 104	72.93 164	83.50 101	45.79 368	69.47 264	80.14 169	65.22 95	81.74 113	87.08 148	61.82 198	81.07 145	56.21 268	94.98 25	91.93 8

NR-MVSNet		73.62 127	74.05 131	72.33 185	83.50 101	43.71 394	65.65 347	77.32 226	64.32 107	75.59 231	87.08 148	62.45 187	81.34 137	54.90 287	95.63 8	91.93 8

SD-MVS		80.28 56	81.55 54	76.47 98	83.57 100	67.83 102	83.39 56	85.35 40	64.42 106	86.14 48	87.07 150	74.02 59	80.97 149	77.70 33	92.32 90	80.62 277
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
旧先验1					84.55 86	60.36 194		63.69 389			87.05 151	54.65 293			83.34 316	69.66 437

ttmdpeth		56.40 422	55.45 433	59.25 416	55.63 521	40.69 426	58.94 438	49.72 480	36.22 480	65.39 418	86.97 152	23.16 520	56.69 451	42.30 404	80.74 372	80.36 283

PatchT		53.35 447	56.47 418	43.99 510	64.19 458	17.46 546	59.15 433	43.10 518	52.11 272	54.74 504	86.95 153	29.97 487	49.98 477	43.62 392	74.40 454	64.53 491

wuyk23d		61.97 360	66.25 294	49.12 486	58.19 509	60.77 191	66.32 337	52.97 464	55.93 203	90.62 5	86.91 154	73.07 65	35.98 539	20.63 542	91.63 99	50.62 524

UniMVSNet_NR-MVSNet		74.90 112	75.65 102	72.64 177	83.04 111	45.79 368	69.26 270	78.81 198	66.66 79	81.74 113	86.88 155	63.26 175	81.07 145	56.21 268	94.98 25	91.05 13

E5new		73.42 132	74.46 117	70.29 223	74.61 260	47.14 345	71.85 220	83.01 94	56.07 196	77.28 184	86.81 156	71.54 79	77.15 224	64.59 153	84.39 294	86.59 77

E6new		73.42 132	74.46 117	70.29 223	74.60 262	47.14 345	71.86 218	82.99 96	56.07 196	77.28 184	86.81 156	71.55 77	77.14 226	64.59 153	84.39 294	86.59 77

E6		73.42 132	74.46 117	70.29 223	74.60 262	47.14 345	71.86 218	82.99 96	56.07 196	77.28 184	86.81 156	71.55 77	77.14 226	64.59 153	84.39 294	86.59 77

E5		73.42 132	74.46 117	70.29 223	74.61 260	47.14 345	71.85 220	83.01 94	56.07 196	77.28 184	86.81 156	71.54 79	77.15 224	64.59 153	84.39 294	86.59 77

EPP-MVSNet		73.86 125	73.38 147	75.31 115	78.19 185	53.35 269	80.45 79	77.32 226	65.11 98	76.47 216	86.80 160	49.47 331	83.77 88	53.89 302	92.72 83	88.81 43

viewmacassd2359aftdt		71.41 190	72.29 177	68.78 270	71.32 334	44.81 380	70.11 251	81.51 131	52.64 262	74.95 252	86.79 161	66.02 148	74.50 270	62.43 185	84.86 277	87.03 70

TinyColmap		67.98 263	69.28 236	64.08 339	67.98 401	46.82 352	70.04 252	75.26 253	53.05 255	77.36 182	86.79 161	59.39 237	72.59 299	45.64 381	88.01 200	72.83 399

test_prior2							75.57 150		58.92 158	76.53 213	86.78 163	67.83 128		69.81 103	92.76 82

RPMNet		65.77 302	65.08 320	67.84 286	66.37 428	48.24 321	70.93 239	86.27 20	54.66 220	61.35 462	86.77 164	33.29 446	85.67 52	55.93 270	70.17 489	69.62 438

TEST9					85.47 69	69.32 87	76.42 135	78.69 203	53.73 245	76.97 191	86.74 165	66.84 136	81.10 143

train_agg		76.38 90	76.55 94	75.86 106	85.47 69	69.32 87	76.42 135	78.69 203	54.00 240	76.97 191	86.74 165	66.60 142	81.10 143	72.50 82	91.56 101	77.15 341

balanced_ft_v1		71.65 184	72.22 180	69.92 241	74.26 268	45.74 370	81.54 70	79.66 179	53.65 248	79.77 138	86.74 165	51.20 318	80.64 155	58.70 236	84.47 289	83.40 190

test_8					85.09 76	67.89 100	76.26 142	78.66 205	54.00 240	76.89 195	86.72 168	66.60 142	80.89 153

MVS_Test		69.84 224	70.71 213	67.24 298	67.49 411	43.25 401	69.87 256	81.22 142	52.69 261	71.57 337	86.68 169	62.09 194	74.51 269	66.05 141	78.74 407	83.96 168

CR-MVSNet		58.96 393	58.49 396	60.36 406	66.37 428	48.24 321	70.93 239	56.40 444	32.87 502	61.35 462	86.66 170	33.19 447	63.22 414	48.50 352	70.17 489	69.62 438

Patchmtry		60.91 377	63.01 348	54.62 453	66.10 435	26.27 530	67.47 311	56.40 444	54.05 239	72.04 324	86.66 170	33.19 447	60.17 428	43.69 391	87.45 210	77.42 332

OMC-MVS		79.41 62	78.79 70	81.28 32	80.62 145	70.71 73	80.91 75	84.76 54	62.54 128	81.77 111	86.65 172	71.46 82	83.53 94	67.95 121	92.44 85	89.60 24

VPNet		65.58 305	67.56 269	59.65 413	79.72 157	30.17 511	60.27 423	62.14 398	54.19 236	71.24 343	86.63 173	58.80 247	67.62 375	44.17 390	90.87 130	81.18 258

IterMVS-LS		73.01 148	73.12 155	72.66 176	73.79 285	49.90 298	71.63 226	78.44 208	58.22 165	80.51 131	86.63 173	58.15 256	79.62 172	62.51 182	88.20 194	88.48 46
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testdata				64.13 338	85.87 64	63.34 160		61.80 404	47.83 348	76.42 218	86.60 175	48.83 340	62.31 418	54.46 294	81.26 358	66.74 467

LFMVS		67.06 284	67.89 265	64.56 334	78.02 189	38.25 454	70.81 242	59.60 417	65.18 96	71.06 345	86.56 176	43.85 370	75.22 256	46.35 373	89.63 160	80.21 287

CNVR-MVS		78.49 71	78.59 73	78.16 74	85.86 65	67.40 107	78.12 112	81.50 132	63.92 110	77.51 178	86.56 176	68.43 117	84.82 73	73.83 68	91.61 100	82.26 234

E4		72.74 159	73.54 142	70.35 220	74.85 251	46.82 352	69.53 261	82.80 101	55.60 206	76.23 220	86.50 178	69.87 102	77.45 217	63.72 169	82.77 324	86.76 74

FMVSNet2		67.48 271	68.21 259	65.29 325	73.14 297	38.94 447	68.81 285	71.21 312	54.81 214	76.73 204	86.48 179	48.63 343	74.60 268	47.98 359	86.11 248	82.35 230

baseline		73.10 143	73.96 133	70.51 215	71.46 332	46.39 364	72.08 207	84.40 69	55.95 202	76.62 207	86.46 180	67.20 131	78.03 208	64.22 161	87.27 220	87.11 68

WR-MVS		71.20 194	72.48 172	67.36 295	84.98 78	35.70 479	64.43 373	68.66 348	65.05 99	81.49 117	86.43 181	57.57 266	76.48 239	50.36 329	93.32 75	89.90 22

UniMVSNet (Re)		75.00 109	75.48 105	73.56 144	83.14 106	47.92 327	70.41 248	81.04 148	63.67 114	79.54 140	86.37 182	62.83 181	81.82 129	57.10 257	95.25 16	90.94 15

PC_three_1452									46.98 361	81.83 110	86.28 183	66.55 144	84.47 79	63.31 177	90.78 131	83.49 183

DP-MVS		78.44 73	79.29 67	75.90 105	81.86 130	65.33 134	79.05 99	84.63 62	74.83 21	80.41 132	86.27 184	71.68 76	83.45 97	62.45 184	92.40 87	78.92 308

ab-mvs		64.11 328	65.13 316	61.05 393	71.99 324	38.03 458	67.59 307	68.79 346	49.08 328	65.32 420	86.26 185	58.02 263	66.85 389	39.33 430	79.79 395	78.27 318

NCCC		78.25 74	78.04 80	78.89 61	85.61 67	69.45 83	79.80 93	80.99 150	65.77 85	75.55 232	86.25 186	67.42 129	85.42 56	70.10 99	90.88 129	81.81 248

FA-MVS(test-final)		71.27 193	71.06 205	71.92 194	73.96 280	52.32 276	76.45 133	76.12 244	59.07 156	74.04 279	86.18 187	52.18 309	79.43 176	59.75 224	81.76 340	84.03 167

ITE_SJBPF				80.35 41	76.94 212	73.60 51		80.48 161	66.87 75	83.64 88	86.18 187	70.25 98	79.90 169	61.12 201	88.95 183	87.56 59

原ACMM1				73.90 135	85.90 62	65.15 138		81.67 128	50.97 293	74.25 272	86.16 189	61.60 201	83.54 93	56.75 260	91.08 120	73.00 395

fmvsm_s_conf0.5_n_9		74.56 116	74.30 124	75.34 114	77.17 203	64.87 140	72.62 197	76.17 243	54.54 225	78.32 162	86.14 190	65.14 163	75.72 249	73.10 73	85.55 256	85.42 111

UGNet		70.20 216	69.05 241	73.65 138	76.24 229	63.64 155	75.87 148	72.53 287	61.48 135	60.93 468	86.14 190	52.37 308	77.12 228	50.67 325	85.21 263	80.17 288
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
OPU-MVS				78.65 64	83.44 104	66.85 115	83.62 51				86.12 192	66.82 137	86.01 36	61.72 192	89.79 159	83.08 204

新几何1				69.99 238	88.37 34	71.34 64		62.08 400	43.85 405	74.99 251	86.11 193	52.85 304	70.57 336	50.99 323	83.23 318	68.05 456

KinetiMVS		72.61 163	72.54 170	72.82 171	71.47 331	55.27 250	68.54 295	76.50 237	61.70 134	74.95 252	86.08 194	59.17 241	76.95 230	69.96 101	84.45 290	86.24 87

mvs_anonymous		65.08 311	65.49 307	63.83 343	63.79 461	37.60 463	66.52 334	69.82 325	43.44 414	73.46 293	86.08 194	58.79 248	71.75 321	51.90 315	75.63 441	82.15 236

114514_t		73.40 137	73.33 151	73.64 139	84.15 94	57.11 235	78.20 110	80.02 171	43.76 408	72.55 312	86.07 196	64.00 171	83.35 99	60.14 215	91.03 121	80.45 281

NP-MVS					83.34 105	63.07 163					85.97 197

HQP-MVS		75.24 104	75.01 110	75.94 104	82.37 120	58.80 217	77.32 120	84.12 79	59.08 153	71.58 334	85.96 198	58.09 258	85.30 60	67.38 131	89.16 173	83.73 178

Anonymous202405211		66.02 299	66.89 287	63.43 355	74.22 271	38.14 455	59.00 436	66.13 367	63.33 121	69.76 366	85.95 199	51.88 310	70.50 337	44.23 389	87.52 207	81.64 253

Anonymous20240521		63.55 333	66.07 299	55.99 446	66.18 433	44.04 391	68.77 288	68.80 345	46.99 360	72.57 311	85.84 200	39.87 408	50.22 476	53.40 310	92.23 92	73.71 390

JIA-IIPM		54.03 441	51.62 462	61.25 391	59.14 502	55.21 255	59.10 435	47.72 492	50.85 295	50.31 523	85.81 201	20.10 534	63.97 409	36.16 469	55.41 537	64.55 490

test222					87.30 37	69.15 92	67.85 305	59.59 418	41.06 440	73.05 305	85.72 202	48.03 348			80.65 375	66.92 463

KD-MVS_self_test		66.38 293	67.51 270	62.97 363	61.76 478	34.39 488	58.11 451	75.30 252	50.84 296	77.12 190	85.42 203	56.84 276	69.44 355	51.07 322	91.16 113	85.08 123

E2		71.98 178	72.60 167	70.13 233	74.09 275	46.61 356	69.15 274	82.56 110	54.40 226	75.32 243	85.35 204	68.51 113	77.34 219	62.30 186	81.74 342	86.44 84

E3		71.98 178	72.60 167	70.13 233	74.09 275	46.61 356	69.15 274	82.56 110	54.40 226	75.31 244	85.35 204	68.51 113	77.34 219	62.30 186	81.75 341	86.44 84

viewdifsd2359ckpt07		70.24 213	71.30 200	67.05 303	70.55 350	43.90 392	67.15 322	77.48 224	53.60 250	75.49 235	85.35 204	71.42 84	72.13 308	59.03 231	81.60 351	85.12 120

DeepC-MVS_fast	69.89 7	77.17 84	76.33 96	79.70 47	83.90 96	67.94 99	80.06 89	83.75 84	56.73 189	74.88 255	85.32 207	65.54 155	87.79 2	65.61 147	91.14 115	83.35 194
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepPCF-MVS	71.07 5	78.48 72	77.14 90	82.52 16	84.39 91	77.04 29	76.35 138	84.05 81	56.66 190	80.27 134	85.31 208	68.56 112	87.03 11	67.39 129	91.26 109	83.50 182

v2v482		72.55 166	72.58 169	72.43 182	72.92 308	46.72 354	71.41 230	79.13 193	55.27 209	81.17 122	85.25 209	55.41 289	81.13 142	67.25 135	85.46 257	89.43 26

QAPM		69.18 239	69.26 237	68.94 265	71.61 329	52.58 275	80.37 82	78.79 201	49.63 314	73.51 290	85.14 210	53.66 299	79.12 179	55.11 281	75.54 442	75.11 372

test_fmvsmconf0.01_n		73.91 123	73.64 139	74.71 119	69.79 370	66.25 123	75.90 147	79.90 174	46.03 372	76.48 215	85.02 211	67.96 126	73.97 280	74.47 60	87.22 226	83.90 171

FE-MVS		68.29 259	66.96 284	72.26 187	74.16 273	54.24 261	77.55 117	73.42 272	57.65 175	72.66 310	84.91 212	32.02 464	81.49 136	48.43 353	81.85 338	81.04 261

viewmanbaseed2359cas		70.24 213	70.83 209	68.48 275	69.99 365	44.55 385	69.48 263	81.01 149	50.87 294	73.61 288	84.84 213	64.00 171	74.31 275	60.24 210	83.43 315	86.56 81

v1144		73.29 140	73.39 146	73.01 158	74.12 274	48.11 323	72.01 210	81.08 147	53.83 244	81.77 111	84.68 214	58.07 261	81.91 128	68.10 116	86.86 235	88.99 38

fmvsm_s_conf0.5_n_3		72.97 152	74.13 129	69.47 249	71.40 333	58.36 223	73.07 190	80.64 157	56.86 185	75.49 235	84.67 215	67.86 127	72.33 306	75.68 45	81.54 354	77.73 331

BP-MVS1		71.60 185	70.06 219	76.20 102	74.07 277	55.22 251	74.29 174	73.44 271	57.29 179	73.87 286	84.65 216	32.57 454	83.49 95	72.43 83	87.94 202	89.89 23

MVStest1		55.38 432	54.97 440	56.58 443	43.72 547	40.07 436	59.13 434	47.09 496	34.83 489	76.53 213	84.65 216	13.55 550	53.30 462	55.04 286	80.23 383	76.38 354

3Dnovator	65.95 11	71.50 187	71.22 202	72.34 184	73.16 296	63.09 162	78.37 106	78.32 210	57.67 173	72.22 318	84.61 218	54.77 291	78.47 192	60.82 204	81.07 364	75.45 365

v1192		73.40 137	73.42 145	73.32 148	74.65 259	48.67 313	72.21 204	81.73 127	52.76 260	81.85 109	84.56 219	57.12 272	82.24 123	68.58 112	87.33 216	89.06 35

mvsmamba		68.87 244	67.30 277	73.57 143	76.58 224	53.70 266	84.43 42	74.25 263	45.38 381	76.63 206	84.55 220	35.85 434	85.27 61	49.54 337	78.49 412	81.75 251

EC-MVSNet		77.08 85	77.39 87	76.14 103	76.86 220	56.87 237	80.32 84	87.52 12	63.45 118	74.66 260	84.52 221	69.87 102	84.94 69	69.76 104	89.59 162	86.60 76

USDC		62.80 346	63.10 345	61.89 377	65.19 446	43.30 400	67.42 312	74.20 265	35.80 485	72.25 317	84.48 222	45.67 357	71.95 314	37.95 447	84.97 266	70.42 430

viewcassd2359sk11		71.41 190	71.89 184	69.98 239	73.50 288	46.46 361	68.91 280	82.39 114	53.62 249	74.57 264	84.41 223	67.40 130	77.27 221	61.35 197	80.89 366	86.21 90

tttt0517		69.46 231	67.79 268	74.46 122	75.34 242	52.72 273	75.05 156	63.27 393	54.69 219	78.87 150	84.37 224	26.63 500	81.15 141	63.95 165	87.93 203	89.51 25

PCF-MVS	63.80 13	72.70 161	71.69 189	75.72 108	78.10 186	60.01 199	73.04 192	81.50 132	45.34 382	79.66 139	84.35 225	65.15 161	82.65 112	48.70 349	89.38 170	84.50 155
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
v1240		73.06 146	73.14 153	72.84 170	74.74 255	47.27 343	71.88 217	81.11 144	51.80 276	82.28 103	84.21 226	56.22 283	82.34 120	68.82 111	87.17 231	88.91 40

SSM_0407		72.15 175	71.85 186	73.06 157	76.92 213	55.22 251	73.59 181	79.83 175	53.69 246	73.08 301	84.18 227	62.26 191	81.98 126	58.21 243	84.91 273	81.99 241

SSM_0404		72.51 167	72.15 182	73.60 141	78.20 184	55.86 244	74.41 171	79.83 175	53.69 246	73.98 280	84.18 227	62.26 191	82.50 114	58.21 243	84.60 284	82.43 228

fmvsm_l_conf0.5_n_3		71.98 178	71.68 190	72.88 168	72.84 310	64.15 151	73.48 184	77.11 231	48.97 332	71.31 342	84.18 227	67.98 125	71.60 324	68.86 110	80.43 379	82.89 210

fmvsm_s_conf0.5_n_8		72.87 156	72.85 161	72.93 164	72.25 319	59.01 214	72.35 201	80.13 170	56.32 193	75.74 227	84.12 230	60.14 224	75.05 262	71.71 87	82.90 321	84.75 137

v148		69.38 234	69.39 231	69.36 251	69.14 379	44.56 383	68.83 283	72.70 285	54.79 217	78.59 155	84.12 230	54.69 292	76.74 237	59.40 227	82.20 331	86.79 72

v144192		72.99 150	73.06 157	72.77 172	74.58 264	47.48 338	71.90 216	80.44 163	51.57 279	81.46 118	84.11 232	58.04 262	82.12 124	67.98 120	87.47 209	88.70 45

fmvsm_s_conf0.5_n_5		71.46 189	71.62 193	70.99 208	73.89 283	59.95 200	73.02 193	73.08 273	45.15 389	77.30 183	84.06 233	64.73 167	70.08 345	71.20 88	82.10 333	82.92 209

fmvsm_s_conf0.5_n_10		72.30 171	72.02 183	73.15 153	70.76 342	59.05 212	73.40 186	79.63 180	48.80 334	75.39 241	84.03 234	59.60 235	75.18 261	72.85 76	83.68 312	85.21 118

NormalMVS		76.15 91	75.08 109	79.36 52	83.87 98	70.01 80	79.92 91	84.34 70	58.60 161	75.21 245	84.02 235	52.85 304	81.82 129	61.45 194	95.50 10	86.24 87

SymmetryMVS		74.00 121	72.85 161	77.43 86	85.17 74	70.01 80	79.92 91	68.48 350	58.60 161	75.21 245	84.02 235	52.85 304	81.82 129	61.45 194	89.99 152	80.47 280

F-COLMAP		75.29 102	73.99 132	79.18 54	81.73 131	71.90 59	81.86 68	82.98 98	59.86 150	72.27 316	84.00 237	64.56 168	83.07 104	51.48 317	87.19 229	82.56 225

viewdifsd2359ckpt11		69.22 236	69.68 228	67.83 287	68.17 396	46.57 358	66.42 335	68.93 338	50.60 300	77.47 180	83.95 238	68.16 119	73.84 285	58.49 239	84.92 271	83.10 201

viewmsd2359difaftdt		69.22 236	69.68 228	67.83 287	68.17 396	46.57 358	66.42 335	68.93 338	50.60 300	77.48 179	83.94 239	68.16 119	73.84 285	58.49 239	84.92 271	83.10 201

RoMa-HiRes		73.61 128	73.51 143	73.92 134	82.27 124	81.71 3	77.59 114	64.83 380	51.32 288	88.72 16	83.92 240	60.47 219	61.70 421	60.01 218	92.44 85	78.34 315

test_fmvsmconf0.1_n		73.26 141	72.82 164	74.56 121	69.10 380	66.18 125	74.65 168	79.34 188	45.58 376	75.54 233	83.91 241	67.19 132	73.88 283	73.26 72	86.86 235	83.63 180

v1921920		72.96 153	72.98 159	72.89 167	74.67 256	47.58 336	71.92 215	80.69 154	51.70 278	81.69 115	83.89 242	56.58 279	82.25 122	68.34 114	87.36 213	88.82 42

MIMVSNet		54.39 438	56.12 423	49.20 484	72.57 312	30.91 507	59.98 426	48.43 490	41.66 434	55.94 495	83.86 243	41.19 399	50.42 472	26.05 525	75.38 445	66.27 472

GDP-MVS		70.84 202	69.24 238	75.62 110	76.44 226	55.65 247	74.62 169	82.78 104	49.63 314	72.10 321	83.79 244	31.86 465	82.84 109	64.93 151	87.01 234	88.39 50

MCST-MVS		73.42 132	73.34 150	73.63 140	81.28 138	59.17 208	74.80 162	83.13 93	45.50 377	72.84 306	83.78 245	65.15 161	80.99 147	64.54 157	89.09 181	80.73 273

dcpmvs_2		71.02 199	72.65 166	66.16 317	76.06 235	50.49 289	71.97 211	79.36 187	50.34 304	82.81 97	83.63 246	64.38 169	67.27 380	61.54 193	83.71 310	80.71 275

E3new		70.94 201	71.30 200	69.86 243	72.98 307	46.34 365	68.74 290	82.28 117	53.01 256	73.95 282	83.57 247	66.41 145	77.21 222	60.68 206	80.06 386	86.03 95

OpenMVS	62.51 15	68.76 247	68.75 247	68.78 270	70.56 348	53.91 264	78.29 107	77.35 225	48.85 333	70.22 354	83.52 248	52.65 307	76.93 231	55.31 279	81.99 334	75.49 364

h-mvs33		73.08 144	71.61 194	77.48 84	83.89 97	72.89 57	70.47 246	71.12 313	54.28 231	77.89 167	83.41 249	49.04 337	80.98 148	63.62 172	90.77 133	78.58 312

TAPA-MVS	65.27 12	75.16 105	74.29 125	77.77 82	74.86 250	68.08 97	77.89 113	84.04 82	55.15 211	76.19 222	83.39 250	66.91 135	80.11 167	60.04 217	90.14 146	85.13 119
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FMVSNet5		55.08 435	55.54 431	53.71 456	65.80 437	33.50 494	56.22 463	52.50 466	43.72 411	61.06 465	83.38 251	25.46 508	54.87 456	30.11 509	81.64 350	72.75 400

VNet		64.01 330	65.15 315	60.57 399	73.28 294	35.61 480	57.60 453	67.08 359	54.61 221	66.76 407	83.37 252	56.28 282	66.87 387	42.19 406	85.20 264	79.23 302

Vis-MVSNet (Re-imp)		62.74 349	63.21 343	61.34 389	72.19 321	31.56 503	67.31 317	53.87 456	53.60 250	69.88 363	83.37 252	40.52 404	70.98 332	41.40 414	86.78 239	81.48 255

GeoE		73.14 142	73.77 137	71.26 204	78.09 187	52.64 274	74.32 172	79.56 185	56.32 193	76.35 219	83.36 254	70.76 92	77.96 209	63.32 176	81.84 339	83.18 199

PAPM_NR		73.91 123	74.16 128	73.16 151	81.90 129	53.50 267	81.28 72	81.40 135	66.17 83	73.30 296	83.31 255	59.96 226	83.10 103	58.45 241	81.66 349	82.87 212

CS-MVS		76.51 89	76.00 99	78.06 78	77.02 209	64.77 141	80.78 76	82.66 107	60.39 145	74.15 273	83.30 256	69.65 105	82.07 125	69.27 108	86.75 240	87.36 61

FMVSNet3		65.00 312	65.16 313	64.52 335	69.47 374	37.56 464	66.63 331	70.38 320	51.55 280	74.72 257	83.27 257	37.89 424	74.44 272	47.12 364	85.37 258	81.57 254

usedtu_dtu_shiyan2		62.25 356	62.27 355	62.18 373	77.08 206	52.84 272	62.56 394	56.33 446	52.43 266	64.22 435	83.26 258	48.47 346	58.06 446	25.75 529	90.34 141	75.64 362

test_fmvsmconf_n		72.91 154	72.40 175	74.46 122	68.62 385	66.12 126	74.21 176	78.80 200	45.64 375	74.62 262	83.25 259	66.80 140	73.86 284	72.97 75	86.66 242	83.39 191

viewmamba		69.26 235	69.34 234	69.03 261	64.17 459	47.67 335	67.23 321	76.95 233	52.82 259	73.15 300	83.23 260	62.99 179	74.06 279	63.71 170	79.80 394	85.36 113

viewdifsd2359ckpt09		72.87 156	72.43 174	74.17 129	74.45 265	51.70 277	76.39 137	84.50 67	49.48 319	75.34 242	83.23 260	63.12 176	82.43 117	56.99 259	88.41 190	88.37 51

V42		71.06 196	70.83 209	71.72 195	67.25 413	47.14 345	65.94 341	80.35 166	51.35 285	83.40 90	83.23 260	59.25 239	78.80 185	65.91 143	80.81 370	89.23 31

test20.03		55.74 428	57.51 408	50.42 475	59.89 496	32.09 500	50.63 498	49.01 486	50.11 308	65.07 422	83.23 260	45.61 358	48.11 492	30.22 508	83.82 304	71.07 425

CNLPA		73.44 131	73.03 158	74.66 120	78.27 183	75.29 37	75.99 146	78.49 207	65.39 91	75.67 229	83.22 264	61.23 207	66.77 391	53.70 305	85.33 261	81.92 245

TestfortrainingZip				73.58 142	79.21 166	57.65 230	86.10 28	81.22 142	72.34 42	72.08 323	83.19 265	58.95 244	83.71 89		84.76 278	79.38 300

mamba_0408		70.32 212	69.35 232	73.24 149	76.92 213	55.22 251	56.61 459	79.27 190	52.14 269	73.08 301	83.14 266	60.53 216	82.50 114	57.51 250	84.91 273	81.99 241

SSM_04072		67.23 279	69.35 232	60.89 396	76.92 213	55.22 251	56.61 459	79.27 190	52.14 269	73.08 301	83.14 266	60.53 216	45.46 508	57.51 250	84.91 273	81.99 241

ALIKED-LG		64.85 314	64.54 323	65.79 323	74.03 278	74.67 42	73.55 182	67.52 357	36.17 481	78.83 151	83.08 268	34.08 440	59.10 433	42.05 410	91.51 103	63.61 494

fmvsm_s_conf0.1_n_2		69.14 240	68.42 253	71.28 203	68.30 393	57.60 231	65.06 358	69.91 323	48.24 339	74.56 265	82.84 269	55.55 288	69.73 349	70.66 96	80.69 374	86.52 82

EPNet		69.10 241	67.32 275	74.46 122	68.33 392	61.27 180	77.56 116	63.57 390	60.95 140	56.62 492	82.75 270	51.53 314	81.24 140	54.36 297	90.20 143	80.88 268
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewdifsd2359ckpt13		69.89 223	69.74 227	70.32 222	70.82 339	48.73 310	72.39 200	81.39 136	48.20 341	72.73 308	82.73 271	62.61 183	76.50 238	55.87 272	80.93 365	85.73 105

SDMVSNet		66.36 294	67.85 267	61.88 378	73.04 303	46.14 367	58.54 446	71.36 304	51.42 282	68.93 378	82.72 272	65.62 154	62.22 419	54.41 295	84.67 280	77.28 334

sd_testset		63.55 333	65.38 309	58.07 430	73.04 303	38.83 449	57.41 454	65.44 374	51.42 282	68.93 378	82.72 272	63.76 174	58.11 444	41.05 417	84.67 280	77.28 334

fmvsm_l_conf0.5_n_9		70.73 205	71.08 204	69.67 246	70.44 354	58.80 217	70.21 250	75.11 256	48.15 343	73.50 291	82.69 274	65.69 153	68.05 372	70.87 93	83.02 319	82.16 235

IterMVS-SCA-FT		67.68 269	66.07 299	72.49 181	73.34 293	58.20 227	63.80 381	65.55 373	48.10 344	76.91 194	82.64 275	45.20 360	78.84 184	61.20 199	77.89 423	80.44 282

FE-MVSNET		62.77 347	64.36 324	57.97 433	70.52 352	33.96 490	61.66 403	67.88 355	50.67 298	73.18 298	82.58 276	48.03 348	68.22 368	43.21 395	81.55 352	71.74 414

DIV-MVS_self_test		68.27 260	68.26 256	68.29 279	64.98 450	43.67 395	65.89 342	74.67 258	50.04 310	76.86 197	82.43 277	48.74 341	75.38 251	60.94 202	89.81 157	85.81 99

cl____		68.26 262	68.26 256	68.29 279	64.98 450	43.67 395	65.89 342	74.67 258	50.04 310	76.86 197	82.42 278	48.74 341	75.38 251	60.92 203	89.81 157	85.80 103

PMatch-Up-SfM		68.45 254	66.90 286	73.11 154	77.17 203	76.10 32	71.60 227	62.67 395	47.32 355	87.78 19	82.41 279	24.19 516	66.58 394	58.86 235	90.11 148	76.66 348

MVS_111021_HR		72.98 151	72.97 160	72.99 159	80.82 143	65.47 132	68.81 285	72.77 283	57.67 173	75.76 226	82.38 280	71.01 89	77.17 223	61.38 196	86.15 245	76.32 355

fmvsm_s_conf0.5_n_2		68.93 243	68.23 258	71.02 207	67.78 405	57.58 232	64.74 365	69.56 327	48.16 342	74.38 270	82.32 281	56.00 285	69.68 352	70.65 97	80.52 378	85.80 103

pmmvs-eth3d		64.41 325	63.27 342	67.82 290	75.81 239	60.18 197	69.49 262	62.05 402	38.81 461	74.13 274	82.23 282	43.76 371	68.65 362	42.53 402	80.63 377	74.63 377

diffmvs_AUTHOR		68.27 260	68.59 251	67.32 297	63.76 462	45.37 373	65.31 353	77.19 229	49.25 323	72.68 309	82.19 283	59.62 234	71.17 328	65.75 145	81.53 355	85.42 111

fmvsm_s_conf0.5_n_4		70.18 217	69.83 226	71.24 205	71.65 328	58.59 222	69.29 269	71.66 296	48.69 335	71.62 331	82.11 284	59.94 227	70.03 346	74.52 58	78.96 405	85.10 121

AstraMVS		67.11 281	66.84 289	67.92 283	70.75 343	51.36 281	64.77 364	67.06 360	49.03 330	75.40 238	82.05 285	51.26 317	70.65 334	58.89 234	82.32 330	81.77 250

PMatch-SfM		67.96 264	66.40 292	72.63 178	78.06 188	75.26 38	71.85 220	59.63 416	46.07 370	86.78 37	82.02 286	26.32 502	66.37 396	57.00 258	89.87 156	76.27 356

MGCFI-Net		71.70 183	73.10 156	67.49 293	73.23 295	43.08 402	72.06 208	82.43 113	54.58 222	75.97 224	82.00 287	72.42 70	75.22 256	57.84 248	87.34 215	84.18 163

alignmvs		70.54 208	71.00 206	69.15 257	73.50 288	48.04 326	69.85 257	79.62 181	53.94 243	76.54 212	82.00 287	59.00 243	74.68 267	57.32 253	87.21 227	84.72 140

MSLP-MVS++		74.48 117	75.78 101	70.59 213	84.66 83	62.40 166	78.65 102	84.24 76	60.55 144	77.71 174	81.98 289	63.12 176	77.64 215	62.95 180	88.14 195	71.73 415

DP-MVS Recon		73.57 130	72.69 165	76.23 101	82.85 115	63.39 159	74.32 172	82.96 99	57.75 171	70.35 352	81.98 289	64.34 170	84.41 81	49.69 334	89.95 153	80.89 267

onestephybrid01		68.67 252	68.21 259	70.07 236	64.40 457	49.83 304	67.51 309	76.41 239	51.08 291	71.78 326	81.97 291	59.69 233	75.32 255	59.85 220	81.20 359	85.06 125

LuminaMVS		71.15 195	70.79 211	72.24 190	77.20 202	58.34 224	72.18 205	76.20 242	54.91 213	77.74 172	81.93 292	49.17 336	76.31 241	62.12 188	85.66 255	82.07 238

dtuplus		65.20 308	64.80 322	66.40 314	65.25 445	44.86 379	64.55 370	72.19 294	43.76 408	72.09 322	81.87 293	57.49 268	71.49 325	48.79 347	77.23 429	82.85 214

BH-RMVSNet		68.69 251	68.20 261	70.14 232	76.40 227	53.90 265	64.62 368	73.48 269	58.01 168	73.91 284	81.78 294	59.09 242	78.22 203	48.59 350	77.96 421	78.31 317

EG-PatchMatch MVS		70.70 206	70.88 208	70.16 231	82.64 119	58.80 217	71.48 228	73.64 267	54.98 212	76.55 211	81.77 295	61.10 211	78.94 183	54.87 288	80.84 369	72.74 401

MVS_111021_LR		72.10 176	71.82 188	72.95 161	79.53 160	73.90 49	70.45 247	66.64 362	56.87 184	76.81 200	81.76 296	68.78 110	71.76 320	61.81 189	83.74 307	73.18 393

AdaColmap		74.22 118	74.56 115	73.20 150	81.95 128	60.97 185	79.43 94	80.90 151	65.57 87	72.54 313	81.76 296	70.98 90	85.26 62	47.88 360	90.00 150	73.37 391

hybridnocas07		66.30 297	66.22 295	66.51 313	60.68 486	44.53 386	64.01 379	74.60 260	48.26 338	70.21 355	81.74 298	56.61 277	71.06 330	60.70 205	79.20 402	83.94 170

fmvsm_s_conf0.5_n_6		70.08 218	69.97 220	70.39 216	72.99 306	58.93 215	68.84 281	76.40 240	49.08 328	68.75 386	81.65 299	57.34 269	71.97 313	70.91 92	83.81 305	80.26 285

sasdasda		72.29 173	73.38 147	69.04 259	74.23 269	47.37 340	73.93 179	83.18 90	54.36 229	76.61 208	81.64 300	72.03 72	75.34 253	57.12 255	87.28 218	84.40 156

canonicalmvs		72.29 173	73.38 147	69.04 259	74.23 269	47.37 340	73.93 179	83.18 90	54.36 229	76.61 208	81.64 300	72.03 72	75.34 253	57.12 255	87.28 218	84.40 156

ALIKED-MNN		63.44 335	63.42 338	63.48 351	73.99 279	70.97 69	71.80 224	66.48 364	32.46 503	71.87 325	81.60 302	36.54 431	58.50 439	42.45 403	93.63 69	60.97 508

fmvsm_s_conf0.5_n_11		71.06 196	70.91 207	71.51 199	72.09 323	59.40 203	73.49 183	79.97 173	50.98 292	68.33 391	81.50 303	61.82 198	72.64 295	69.54 107	80.43 379	82.51 226

DKM-HiRes		70.49 209	69.89 222	72.31 186	81.51 134	80.92 7	73.23 189	58.80 423	49.23 324	84.44 78	81.39 304	49.91 327	61.22 424	59.28 229	91.22 111	74.79 374

MVS-HIRNet		45.53 490	47.29 487	40.24 519	62.29 475	26.82 525	56.02 466	37.41 541	29.74 517	43.69 542	81.27 305	33.96 441	55.48 454	24.46 534	56.79 533	38.43 541

CMPMVS	48.73 20	61.54 369	60.89 373	63.52 350	61.08 482	51.55 279	68.07 304	68.00 353	33.88 495	65.87 415	81.25 306	37.91 423	67.71 373	49.32 340	82.60 326	71.31 420
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
viewmambaseed2359dif		65.63 303	65.13 316	67.11 302	64.57 455	44.73 382	64.12 376	72.48 290	43.08 421	71.59 332	81.17 307	58.90 246	72.46 300	52.94 311	77.33 427	84.13 166

testgi		54.00 443	56.86 414	45.45 503	58.20 508	25.81 533	49.05 504	49.50 482	45.43 380	67.84 395	81.17 307	51.81 313	43.20 522	29.30 513	79.41 400	67.34 460

ALIKED-NN		61.86 362	61.18 367	63.92 342	71.72 327	71.04 66	69.24 271	66.41 365	29.80 516	64.25 434	81.10 309	35.56 436	58.35 440	41.25 415	91.30 108	62.35 502

fmvsm_l_conf0.5_n		67.48 271	66.88 288	69.28 254	67.41 412	62.04 169	70.69 243	69.85 324	39.46 454	69.59 367	81.09 310	58.15 256	68.73 360	67.51 126	78.16 420	77.07 346

test_fmvsmvis_n_1920		72.36 169	72.49 171	71.96 192	71.29 336	64.06 153	72.79 196	81.82 125	40.23 450	81.25 121	81.04 311	70.62 93	68.69 361	69.74 105	83.60 313	83.14 200

CL-MVSNet_self_test		62.44 354	63.40 340	59.55 415	72.34 318	32.38 498	56.39 461	64.84 379	51.21 289	67.46 401	81.01 312	50.75 321	63.51 413	38.47 440	88.12 196	82.75 217

fmvsm_s_conf0.1_n_a		67.37 275	66.36 293	70.37 219	70.86 338	61.17 181	74.00 178	57.18 436	40.77 445	68.83 385	80.88 313	63.11 178	67.61 376	66.94 136	74.72 449	82.33 233

hybrid		65.62 304	65.49 307	66.01 319	60.48 488	44.28 389	64.13 375	74.21 264	46.41 366	69.84 364	80.86 314	55.77 286	70.28 342	59.30 228	78.42 414	83.46 187

guyue		66.95 287	66.74 290	67.56 292	70.12 364	51.14 283	65.05 359	68.68 347	49.98 312	74.64 261	80.83 315	50.77 320	70.34 341	57.72 249	82.89 322	81.21 256

SPE-MVS-test		74.89 113	74.23 126	76.86 91	77.01 210	62.94 164	78.98 100	84.61 63	58.62 160	70.17 357	80.80 316	66.74 141	81.96 127	61.74 191	89.40 169	85.69 106

thisisatest0530		67.05 285	65.16 313	72.73 175	73.10 300	50.55 288	71.26 235	63.91 388	50.22 307	74.46 267	80.75 317	26.81 499	80.25 163	59.43 226	86.50 243	87.37 60

PHI-MVS		74.92 110	74.36 123	76.61 94	76.40 227	62.32 168	80.38 81	83.15 92	54.16 237	73.23 297	80.75 317	62.19 193	83.86 85	68.02 118	90.92 126	83.65 179

fmvsm_s_conf0.5_n_7		67.30 276	66.92 285	68.43 276	72.78 311	58.22 226	60.90 414	72.51 289	49.62 316	63.66 447	80.65 319	58.56 251	68.63 363	62.83 181	80.76 371	78.45 314

RoMa-SfM		70.84 202	70.47 216	71.95 193	80.95 141	81.09 6	76.44 134	62.08 400	46.25 368	87.14 35	80.63 320	55.60 287	58.69 437	54.19 299	90.98 122	76.07 360

PLC	62.01 16	71.79 182	70.28 218	76.33 99	80.31 149	68.63 95	78.18 111	81.24 140	54.57 223	67.09 405	80.63 320	59.44 236	81.74 134	46.91 367	84.17 299	78.63 310
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PM-MVS		64.49 322	63.61 335	67.14 301	76.68 222	75.15 39	68.49 297	42.85 521	51.17 290	77.85 169	80.51 322	45.76 356	66.31 397	52.83 312	76.35 435	59.96 510

CANet		73.00 149	71.84 187	76.48 97	75.82 238	61.28 179	74.81 160	80.37 165	63.17 122	62.43 457	80.50 323	61.10 211	85.16 68	64.00 163	84.34 298	83.01 207

IterMVS		63.12 342	62.48 354	65.02 330	66.34 430	52.86 271	63.81 380	62.25 396	46.57 365	71.51 339	80.40 324	44.60 365	66.82 390	51.38 320	75.47 443	75.38 367
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_l_conf0.5_n_a		66.66 288	65.97 302	68.72 272	67.09 416	61.38 178	70.03 253	69.15 332	38.59 462	68.41 389	80.36 325	56.56 280	68.32 367	66.10 140	77.45 426	76.46 353

dtuonlycased		61.79 364	62.24 356	60.43 403	73.00 305	39.07 444	61.74 401	60.61 408	33.09 501	74.10 275	80.34 326	59.20 240	60.39 426	38.34 441	79.76 396	81.83 247

eth_miper_zixun_eth		69.42 232	68.73 249	71.50 200	67.99 400	46.42 362	67.58 308	78.81 198	50.72 297	78.13 165	80.34 326	50.15 326	80.34 161	60.18 212	84.65 282	87.74 56

DPM-MVS		69.98 221	69.22 240	72.26 187	82.69 118	58.82 216	70.53 245	81.23 141	47.79 349	64.16 437	80.21 328	51.32 316	83.12 102	60.14 215	84.95 270	74.83 373

LF4IMVS		67.50 270	67.31 276	68.08 282	58.86 504	61.93 170	71.43 229	75.90 248	44.67 396	72.42 314	80.20 329	57.16 270	70.44 338	58.99 232	86.12 247	71.88 412

CSCG		74.12 120	74.39 121	73.33 147	79.35 162	61.66 174	77.45 119	81.98 123	62.47 130	79.06 148	80.19 330	61.83 197	78.79 186	59.83 221	87.35 214	79.54 297

c3_l		69.82 225	69.89 222	69.61 247	66.24 431	43.48 397	68.12 303	79.61 183	51.43 281	77.72 173	80.18 331	54.61 294	78.15 207	63.62 172	87.50 208	87.20 65

fmvsm_s_conf0.1_n		66.60 289	65.54 306	69.77 244	68.99 382	59.15 209	72.12 206	56.74 441	40.72 447	68.25 394	80.14 332	61.18 210	66.92 383	67.34 133	74.40 454	83.23 198

fmvsm_s_conf0.5_n_a		67.00 286	65.95 303	70.17 230	69.72 371	61.16 182	73.34 187	56.83 439	40.96 442	68.36 390	80.08 333	62.84 180	67.57 377	66.90 138	74.50 453	81.78 249

FPMVS		59.43 391	60.07 381	57.51 437	77.62 198	71.52 62	62.33 396	50.92 474	57.40 177	69.40 370	80.00 334	39.14 415	61.92 420	37.47 453	66.36 509	39.09 540

LoFTR		61.29 370	62.50 353	57.67 436	69.07 381	65.66 131	68.96 278	48.59 488	43.15 420	86.65 39	79.95 335	32.68 453	53.14 463	46.21 375	87.20 228	54.22 520

DKM		69.82 225	69.29 235	71.40 202	80.33 148	80.76 8	73.05 191	60.16 414	47.00 359	85.42 63	79.91 336	48.29 347	58.24 442	57.18 254	92.25 91	75.19 371

thres100view900		61.17 372	61.09 369	61.39 387	72.14 322	35.01 483	65.42 352	56.99 437	55.23 210	70.71 348	79.90 337	32.07 462	72.09 309	35.61 474	81.73 343	77.08 344

new-patchmatchnet		52.89 452	55.76 430	44.26 509	59.94 495	6.31 555	37.36 536	50.76 476	41.10 439	64.28 433	79.82 338	44.77 363	48.43 491	36.24 468	87.61 205	78.03 324

thres600view7		61.82 363	61.38 366	63.12 358	71.81 326	34.93 484	64.64 367	56.99 437	54.78 218	70.33 353	79.74 339	32.07 462	72.42 302	38.61 438	83.46 314	82.02 239

testing3-2		56.85 417	57.62 405	54.53 454	75.84 237	22.23 542	51.26 497	49.10 485	61.04 139	63.74 445	79.73 340	22.29 525	59.44 431	31.16 505	84.43 293	81.92 245

diffmvs		67.42 274	67.50 271	67.20 299	62.26 476	45.21 376	64.87 361	77.04 232	48.21 340	71.74 327	79.70 341	58.40 253	71.17 328	64.99 149	80.27 382	85.22 115
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SSC-MVS3.2		57.01 416	59.50 387	49.57 482	67.73 406	25.95 532	46.68 514	51.75 471	51.41 284	63.84 442	79.66 342	53.28 302	50.34 474	37.85 448	83.28 317	72.41 405

BH-untuned		69.39 233	69.46 230	69.18 256	77.96 191	56.88 236	68.47 298	77.53 222	56.77 187	77.79 170	79.63 343	60.30 223	80.20 166	46.04 377	80.65 375	70.47 428

VortexMVS		65.93 300	66.04 301	65.58 324	67.63 409	47.55 337	64.81 362	72.75 284	47.37 354	75.17 248	79.62 344	49.28 334	71.00 331	55.20 280	82.51 327	78.21 320

PAPM		61.79 364	60.37 380	66.05 318	76.09 232	41.87 411	69.30 268	76.79 236	40.64 448	53.80 508	79.62 344	44.38 366	82.92 106	29.64 512	73.11 466	73.36 392

fmvsm_s_conf0.5_n		66.34 296	65.27 310	69.57 248	68.20 394	59.14 211	71.66 225	56.48 442	40.92 443	67.78 396	79.46 346	61.23 207	66.90 384	67.39 129	74.32 457	82.66 222

XXY-MVS		55.19 433	57.40 409	48.56 490	64.45 456	34.84 486	51.54 494	53.59 458	38.99 460	63.79 444	79.43 347	56.59 278	45.57 506	36.92 459	71.29 481	65.25 483

SD_0403		61.63 367	62.83 350	58.03 431	72.21 320	32.43 497	69.33 267	69.00 337	44.54 398	62.01 458	79.42 348	55.27 290	66.88 386	36.07 471	77.63 425	74.78 375

MonoMVSNet		62.75 348	63.42 338	60.73 398	65.60 440	40.77 425	72.49 199	70.56 318	52.49 264	75.07 249	79.42 348	39.52 413	69.97 348	46.59 371	69.06 495	71.44 417

MDA-MVSNet-bldmvs		62.34 355	61.73 360	64.16 337	61.64 479	49.90 298	48.11 508	57.24 435	53.31 254	80.95 124	79.39 350	49.00 339	61.55 422	45.92 379	80.05 387	81.03 262

icg_test_0407_2		63.88 332	65.59 305	58.75 422	72.47 313	48.64 314	53.19 483	72.98 277	45.33 383	68.91 380	79.37 351	61.91 195	51.11 467	55.06 282	81.11 360	76.49 349

IMVS_0407		67.26 277	67.35 274	66.97 306	72.47 313	48.64 314	69.03 277	72.98 277	45.33 383	68.91 380	79.37 351	61.91 195	75.77 246	55.06 282	81.11 360	76.49 349

IMVS_0404		62.18 359	63.05 346	59.58 414	72.47 313	48.64 314	55.47 469	72.98 277	45.33 383	55.80 498	79.37 351	49.84 328	53.60 461	55.06 282	81.11 360	76.49 349

IMVS_0403		67.07 283	67.08 279	67.03 304	72.47 313	48.64 314	68.44 299	72.98 277	45.33 383	68.63 388	79.37 351	60.38 221	75.97 242	55.06 282	81.11 360	76.49 349

TAMVS		65.31 307	63.75 332	69.97 240	82.23 125	59.76 202	66.78 330	63.37 392	45.20 388	69.79 365	79.37 351	47.42 352	72.17 307	34.48 485	85.15 265	77.99 326

PAPR		69.20 238	68.66 250	70.82 209	75.15 246	47.77 331	75.31 153	81.11 144	49.62 316	66.33 412	79.27 356	61.53 202	82.96 105	48.12 357	81.50 356	81.74 252

Anonymous20231206		54.13 439	55.82 428	49.04 487	70.89 337	35.96 476	51.73 493	50.87 475	34.86 488	62.49 456	79.22 357	42.52 387	44.29 518	27.95 520	81.88 336	66.88 464

OpenMVS_ROB	54.93 17	63.23 341	63.28 341	63.07 359	69.81 367	45.34 374	68.52 296	67.14 358	43.74 410	70.61 349	79.22 357	47.90 350	72.66 294	48.75 348	73.84 461	71.21 422

PVSNet_Blended_VisFu		70.04 219	68.88 244	73.53 145	82.71 117	63.62 156	74.81 160	81.95 124	48.53 337	67.16 404	79.18 359	51.42 315	78.38 198	54.39 296	79.72 397	78.60 311

MVSTER		63.29 340	61.60 364	68.36 277	59.77 497	46.21 366	60.62 418	71.32 305	41.83 433	75.40 238	79.12 360	30.25 483	75.85 243	56.30 267	79.81 392	83.03 206

tpm		50.60 468	52.42 458	45.14 505	65.18 447	26.29 529	60.30 422	43.50 515	37.41 473	57.01 487	79.09 361	30.20 485	42.32 524	32.77 498	66.36 509	66.81 466

test_yl		65.11 309	65.09 318	65.18 327	70.59 346	40.86 422	63.22 390	72.79 281	57.91 169	68.88 382	79.07 362	42.85 384	74.89 264	45.50 383	84.97 266	79.81 290

DCV-MVSNet		65.11 309	65.09 318	65.18 327	70.59 346	40.86 422	63.22 390	72.79 281	57.91 169	68.88 382	79.07 362	42.85 384	74.89 264	45.50 383	84.97 266	79.81 290

test_fmvsm_n_1920		69.63 227	68.45 252	73.16 151	70.56 348	65.86 128	70.26 249	78.35 209	37.69 470	74.29 271	78.89 364	61.10 211	68.10 370	65.87 144	79.07 403	85.53 109

miper_lstm_enhance		61.97 360	61.63 363	62.98 360	60.04 491	45.74 370	47.53 510	70.95 314	44.04 404	73.06 304	78.84 365	39.72 410	60.33 427	55.82 274	84.64 283	82.88 211

PVSNet_BlendedMVS		65.38 306	64.30 325	68.61 273	69.81 367	49.36 306	65.60 349	78.96 195	45.50 377	59.98 471	78.61 366	51.82 311	78.20 204	44.30 387	84.11 300	78.27 318

baseline1		57.82 406	58.36 399	56.19 445	69.17 378	30.76 509	62.94 392	55.21 449	46.04 371	63.83 443	78.47 367	41.20 398	63.68 411	39.44 429	68.99 496	74.13 384

TSAR-MVS + GP.		73.08 144	71.60 195	77.54 83	78.99 177	70.73 72	74.96 157	69.38 329	60.73 143	74.39 269	78.44 368	57.72 265	82.78 110	60.16 213	89.60 161	79.11 303

MVP-Stereo		61.56 368	59.22 388	68.58 274	79.28 163	60.44 193	69.20 272	71.57 298	43.58 412	56.42 493	78.37 369	39.57 412	76.46 240	34.86 481	60.16 526	68.86 447
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
hse-mvs2		72.32 170	70.66 214	77.31 89	83.10 110	71.77 60	69.19 273	71.45 302	54.28 231	77.89 167	78.26 370	49.04 337	79.23 177	63.62 172	89.13 177	80.92 266

patch_mono-2		62.73 350	64.08 329	58.68 425	70.36 357	55.87 243	60.84 415	64.11 387	41.23 438	64.04 438	78.22 371	60.00 225	48.80 484	54.17 300	83.71 310	71.37 418

D2MVS		62.58 352	61.05 370	67.20 299	63.85 460	47.92 327	56.29 462	69.58 326	39.32 455	70.07 359	78.19 372	34.93 438	72.68 293	53.44 308	83.74 307	81.00 264

HY-MVS	49.31 19	57.96 404	57.59 407	59.10 420	66.85 424	36.17 474	65.13 357	65.39 375	39.24 458	54.69 505	78.14 373	44.28 367	67.18 382	33.75 492	70.79 484	73.95 386

Effi-MVS+-dtu		75.43 101	72.28 178	84.91 2	77.05 207	83.58 1	78.47 105	77.70 220	57.68 172	74.89 254	78.13 374	64.80 165	84.26 82	56.46 266	85.32 262	86.88 71

AUN-MVS		70.22 215	67.88 266	77.22 90	82.96 114	71.61 61	69.08 276	71.39 303	49.17 326	71.70 328	78.07 375	37.62 426	79.21 178	61.81 189	89.15 175	80.82 269

cl22		67.14 280	66.51 291	69.03 261	63.20 466	43.46 398	66.88 329	76.25 241	49.22 325	74.48 266	77.88 376	45.49 359	77.40 218	60.64 207	84.59 285	86.24 87

miper_ehance_all_eth		68.36 256	68.16 262	68.98 263	65.14 449	43.34 399	67.07 324	78.92 197	49.11 327	76.21 221	77.72 377	53.48 300	77.92 210	61.16 200	84.59 285	85.68 107

DSMNet-mixed		43.18 502	44.66 501	38.75 521	54.75 525	28.88 518	57.06 456	27.42 548	13.47 545	47.27 531	77.67 378	38.83 416	39.29 536	25.32 532	60.12 527	48.08 526

Test_1112_low_res		58.78 396	58.69 393	59.04 421	79.41 161	38.13 456	57.62 452	66.98 361	34.74 491	59.62 477	77.56 379	42.92 383	63.65 412	38.66 437	70.73 485	75.35 368

API-MVS		70.97 200	71.51 197	69.37 250	75.20 244	55.94 242	80.99 73	76.84 234	62.48 129	71.24 343	77.51 380	61.51 203	80.96 152	52.04 313	85.76 254	71.22 421

ELoFTR		57.63 408	59.55 386	51.85 467	66.16 434	61.46 176	69.66 260	43.94 511	30.20 515	82.28 103	77.47 381	33.76 443	42.30 525	42.10 407	90.40 140	51.81 522

pmmvs4		60.78 379	59.04 390	66.00 320	73.06 302	57.67 229	64.53 371	60.22 412	36.91 476	65.96 414	77.27 382	39.66 411	68.54 365	38.87 435	74.89 448	71.80 413

WBMVS		53.38 445	54.14 446	51.11 472	70.16 361	26.66 526	50.52 500	51.64 472	39.32 455	63.08 453	77.16 383	23.53 518	55.56 453	31.99 500	79.88 390	71.11 424

tfpn200view9		60.35 383	59.97 382	61.51 384	70.78 340	35.35 481	63.27 388	57.47 430	53.00 257	68.31 392	77.09 384	32.45 457	72.09 309	35.61 474	81.73 343	77.08 344

thres400		60.77 380	59.97 382	63.15 357	70.78 340	35.35 481	63.27 388	57.47 430	53.00 257	68.31 392	77.09 384	32.45 457	72.09 309	35.61 474	81.73 343	82.02 239

Effi-MVS+		72.10 176	72.28 178	71.58 196	74.21 272	50.33 291	74.72 165	82.73 105	62.62 127	70.77 347	76.83 386	69.96 101	80.97 149	60.20 211	78.43 413	83.45 189

MVSFormer		69.93 222	69.03 242	72.63 178	74.93 247	59.19 206	83.98 45	75.72 249	52.27 267	63.53 450	76.74 387	43.19 377	80.56 156	72.28 84	78.67 409	78.14 322

jason		64.47 323	62.84 349	69.34 253	76.91 216	59.20 205	67.15 322	65.67 370	35.29 487	65.16 421	76.74 387	44.67 364	70.68 333	54.74 290	79.28 401	78.14 322
jason: jason.
DenseAffine		67.25 278	66.08 297	70.76 210	80.22 150	77.51 25	70.65 244	58.59 425	45.98 373	81.51 116	76.48 389	41.58 394	62.36 416	49.23 342	90.48 137	72.40 406

CostFormer		57.35 413	56.14 422	60.97 394	63.76 462	38.43 451	67.50 310	60.22 412	37.14 475	59.12 479	76.34 390	32.78 450	71.99 312	39.12 434	69.27 494	72.47 404

MDTV_nov1_ep13			54.05 448		65.54 442	29.30 516	59.00 436	55.22 448	35.96 484	52.44 512	75.98 391	30.77 478	59.62 430	38.21 442	73.33 465

SP-SuperGlue		66.58 290	67.36 273	64.24 336	68.59 387	66.47 119	68.14 301	61.29 406	58.07 167	71.67 329	75.95 392	46.37 354	50.95 470	74.72 53	81.46 357	75.29 370

testing3		58.28 401	58.38 398	58.00 432	77.45 201	26.12 531	60.78 416	43.00 520	56.02 200	70.18 356	75.76 393	13.27 551	67.24 381	48.02 358	80.89 366	80.65 276

EU-MVSNet		60.82 378	60.80 375	60.86 397	68.37 390	41.16 418	72.27 202	68.27 352	26.96 525	69.08 372	75.71 394	32.09 461	67.44 378	55.59 277	78.90 406	73.97 385

usedtu_dtu_shiyan1		61.16 373	60.92 371	61.90 375	69.70 372	36.41 472	58.57 444	68.86 342	44.94 393	65.02 423	75.67 395	43.00 381	70.28 342	40.83 420	81.68 347	78.99 305

FE-MVSNET3		61.16 373	60.92 371	61.90 375	69.70 372	36.41 472	58.57 444	68.86 342	44.94 393	65.02 423	75.67 395	43.00 381	70.28 342	40.82 421	81.68 347	78.99 305

SP-LightGlue		66.16 298	66.97 283	63.75 345	68.62 385	66.76 116	68.82 284	62.15 397	57.30 178	70.52 350	75.63 397	43.02 380	48.82 483	75.09 49	81.55 352	75.66 361

HyFIR lowres test		63.01 343	60.47 379	70.61 212	83.04 111	54.10 262	59.93 428	72.24 293	33.67 498	69.00 373	75.63 397	38.69 417	76.93 231	36.60 463	75.45 444	80.81 271

Fast-Effi-MVS+		68.81 246	68.30 255	70.35 220	74.66 258	48.61 318	66.06 339	78.32 210	50.62 299	71.48 340	75.54 399	68.75 111	79.59 174	50.55 328	78.73 408	82.86 213

CDS-MVSNet		64.33 326	62.66 352	69.35 252	80.44 147	58.28 225	65.26 354	65.66 371	44.36 400	67.30 403	75.54 399	43.27 376	71.77 319	37.68 449	84.44 292	78.01 325
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tpm2		56.12 424	54.64 443	60.55 400	66.24 431	36.01 475	68.14 301	56.77 440	33.60 499	58.25 482	75.52 401	30.25 483	74.33 274	33.27 494	69.76 493	71.32 419

CANet_DTU		64.04 329	63.83 331	64.66 333	68.39 388	42.97 404	73.45 185	74.50 262	52.05 273	54.78 503	75.44 402	43.99 369	70.42 339	53.49 307	78.41 415	80.59 278

reproduce_monomvs		58.94 394	58.14 400	61.35 388	59.70 498	40.98 421	60.24 424	63.51 391	45.85 374	68.95 376	75.31 403	18.27 541	65.82 399	51.47 318	79.97 388	77.26 337

DELS-MVS		68.83 245	68.31 254	70.38 217	70.55 350	48.31 319	63.78 382	82.13 120	54.00 240	68.96 375	75.17 404	58.95 244	80.06 168	58.55 238	82.74 325	82.76 216
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
pmmvs5		52.49 456	52.58 456	52.21 465	54.99 524	32.38 498	55.45 470	53.84 457	32.15 506	55.49 499	74.81 405	38.08 421	57.37 448	34.02 488	74.40 454	66.88 464

MSDG		67.47 273	67.48 272	67.46 294	70.70 344	54.69 258	66.90 328	78.17 213	60.88 141	70.41 351	74.76 406	61.22 209	73.18 288	47.38 363	76.87 431	74.49 381

UnsupCasMVSNet_eth		52.26 457	53.29 452	49.16 485	55.08 523	33.67 493	50.03 502	58.79 424	37.67 471	63.43 452	74.75 407	41.82 392	45.83 504	38.59 439	59.42 528	67.98 457

Fast-Effi-MVS+-dtu		70.00 220	68.74 248	73.77 137	73.47 290	64.53 143	71.36 231	78.14 215	55.81 204	68.84 384	74.71 408	65.36 158	75.75 247	52.00 314	79.00 404	81.03 262

MatchFormer		53.09 449	55.03 439	47.30 493	59.31 500	57.25 234	67.30 318	37.25 542	27.23 523	82.61 100	74.56 409	26.23 504	42.89 523	34.73 483	86.00 249	41.75 538

TR-MVS		64.59 320	63.54 337	67.73 291	75.75 240	50.83 287	63.39 386	70.29 321	49.33 320	71.55 338	74.55 410	50.94 319	78.46 193	40.43 425	75.69 440	73.89 387

GA-MVS		62.91 344	61.66 361	66.66 311	67.09 416	44.49 387	61.18 411	69.36 330	51.33 286	69.33 371	74.47 411	36.83 429	74.94 263	50.60 327	74.72 449	80.57 279

CLD-MVS		72.88 155	72.36 176	74.43 125	77.03 208	54.30 260	68.77 288	83.43 89	52.12 271	76.79 202	74.44 412	69.54 106	83.91 84	55.88 271	93.25 76	85.09 122
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CHOSEN 1792x2688		58.09 403	56.30 419	63.45 354	79.95 153	50.93 286	54.07 480	65.59 372	28.56 519	61.53 461	74.33 413	41.09 400	66.52 395	33.91 489	67.69 504	72.92 396

Patchmatch-RL test		59.95 386	59.12 389	62.44 370	72.46 317	54.61 259	59.63 430	47.51 494	41.05 441	74.58 263	74.30 414	31.06 474	65.31 403	51.61 316	79.85 391	67.39 458

cdsmvs_eth3d_5k		17.71 514	23.62 515	0.00 535	0.00 559	0.00 561	0.00 546	70.17 322	0.00 553	0.00 555	74.25 415	68.16 119	0.00 555	0.00 553	0.00 553	0.00 550

lupinMVS		63.36 336	61.49 365	68.97 264	74.93 247	59.19 206	65.80 345	64.52 384	34.68 493	63.53 450	74.25 415	43.19 377	70.62 335	53.88 303	78.67 409	77.10 343

xiu_mvs_v1_base_debu		67.87 265	67.07 280	70.26 227	79.13 170	61.90 171	67.34 313	71.25 308	47.98 345	67.70 397	74.19 417	61.31 204	72.62 296	56.51 263	78.26 417	76.27 356

xiu_mvs_v1_base		67.87 265	67.07 280	70.26 227	79.13 170	61.90 171	67.34 313	71.25 308	47.98 345	67.70 397	74.19 417	61.31 204	72.62 296	56.51 263	78.26 417	76.27 356

xiu_mvs_v1_base_debi		67.87 265	67.07 280	70.26 227	79.13 170	61.90 171	67.34 313	71.25 308	47.98 345	67.70 397	74.19 417	61.31 204	72.62 296	56.51 263	78.26 417	76.27 356

SIFT-MNN		59.60 389	58.57 394	62.71 367	68.39 388	69.16 90	63.67 383	48.13 491	45.22 387	73.92 283	73.85 420	30.71 479	50.57 471	39.45 428	83.78 306	68.40 448

SP-MNN		63.33 337	64.30 325	60.41 405	66.01 436	60.04 198	65.58 350	60.61 408	49.33 320	69.45 368	73.75 421	41.65 393	48.61 487	69.96 101	82.36 329	72.57 402

tpmvs		55.84 426	55.45 433	57.01 440	60.33 489	33.20 495	65.89 342	59.29 419	47.52 353	56.04 494	73.60 422	31.05 475	68.06 371	40.64 424	64.64 513	69.77 436

SCA		58.57 400	58.04 401	60.17 408	70.17 360	41.07 420	65.19 356	53.38 462	43.34 418	61.00 467	73.48 423	45.20 360	69.38 356	40.34 426	70.31 488	70.05 431

Patchmatch-test		47.93 483	49.96 478	41.84 515	57.42 512	24.26 535	48.75 505	41.49 529	39.30 457	56.79 489	73.48 423	30.48 482	33.87 540	29.29 514	72.61 469	67.39 458

SP-NN		62.65 351	63.58 336	59.87 410	64.90 453	59.38 204	64.50 372	60.00 415	50.42 303	66.09 413	73.43 425	43.16 379	46.39 501	71.17 89	78.53 411	73.85 388

ArgMatch-SfM		64.74 318	63.70 334	67.83 287	77.62 198	76.78 30	67.30 318	58.21 426	36.64 478	81.94 108	73.41 426	38.67 418	56.92 449	50.66 326	88.89 184	69.81 434

MDA-MVSNet_test_wron		52.57 455	53.49 451	49.81 479	54.24 526	36.47 470	40.48 530	46.58 498	38.13 465	75.47 237	73.32 427	41.05 402	43.85 520	40.98 418	71.20 482	69.10 445

YYNet1		52.58 454	53.50 449	49.85 478	54.15 527	36.45 471	40.53 529	46.55 499	38.09 466	75.52 234	73.31 428	41.08 401	43.88 519	41.10 416	71.14 483	69.21 443

SIFT-ConvMatch		58.61 399	57.61 406	61.63 382	65.55 441	67.97 98	62.24 397	42.52 522	44.40 399	77.28 184	73.28 429	30.00 486	50.42 472	36.36 465	86.82 238	66.50 469

PatchmatchNet		54.60 437	54.27 445	55.59 449	65.17 448	39.08 443	66.92 327	51.80 470	39.89 451	58.39 480	73.12 430	31.69 468	58.33 441	43.01 399	58.38 532	69.38 442
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPNet_dtu		58.93 395	58.52 395	60.16 409	67.91 403	47.70 334	69.97 254	58.02 427	49.73 313	47.28 530	73.02 431	38.14 420	62.34 417	36.57 464	85.99 250	70.43 429
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_enhance_ethall		65.86 301	65.05 321	68.28 281	61.62 480	42.62 407	64.74 365	77.97 217	42.52 426	73.42 294	72.79 432	49.66 329	77.68 214	58.12 245	84.59 285	84.54 150

SIFT-UMatch		58.13 402	57.37 410	60.42 404	65.49 443	67.10 112	61.52 405	43.57 514	44.20 401	76.80 201	72.60 433	29.70 489	47.95 494	36.61 462	85.82 251	66.20 473

dtuonly		50.13 473	51.25 466	46.77 497	53.07 532	30.10 512	52.41 491	49.25 483	28.98 518	53.76 509	72.59 434	39.83 409	41.82 529	37.58 452	73.80 462	68.37 449

ppachtmachnet_test		60.26 384	59.61 385	62.20 372	67.70 407	44.33 388	58.18 450	60.96 407	40.75 446	65.80 416	72.57 435	41.23 397	63.92 410	46.87 368	82.42 328	78.33 316

SIFT-NN-UMatch		57.27 414	56.18 421	60.54 401	62.85 469	66.67 118	61.19 410	41.27 531	43.01 422	70.01 360	72.44 436	32.76 451	49.32 481	38.19 444	83.87 302	65.63 477

SIFT-NCM-Cal		58.68 397	57.65 404	61.77 380	67.58 410	68.99 94	62.62 393	43.04 519	44.65 397	75.91 225	72.23 437	33.66 444	49.28 482	34.36 486	84.76 278	67.03 462

N_pmnet		52.06 458	51.11 468	54.92 450	59.64 499	71.03 67	37.42 535	61.62 405	33.68 497	57.12 485	72.10 438	37.94 422	31.03 542	29.13 518	71.35 480	62.70 497

SP-DiffGlue		64.90 313	65.69 304	62.51 369	69.18 376	64.39 145	69.79 258	60.46 411	52.50 263	75.70 228	72.08 439	44.17 368	48.59 488	67.84 123	79.52 399	74.54 379

ADS-MVSNet2		48.76 480	47.25 488	53.29 461	55.90 519	40.54 432	47.34 511	54.99 451	31.41 511	50.48 520	72.06 440	31.23 471	54.26 458	25.93 526	55.93 534	65.07 485

ADS-MVSNet		44.62 495	45.58 494	41.73 516	55.90 519	20.83 543	47.34 511	39.94 537	31.41 511	50.48 520	72.06 440	31.23 471	39.31 535	25.93 526	55.93 534	65.07 485

ET-MVSNet_ETH3D		63.32 338	60.69 376	71.20 206	70.15 362	55.66 246	65.02 360	64.32 385	43.28 419	68.99 374	72.05 442	25.46 508	78.19 206	54.16 301	82.80 323	79.74 293

SIFT-NN-CMatch		57.48 410	56.23 420	61.21 392	63.66 464	67.89 100	60.78 416	40.90 535	41.97 431	71.65 330	71.96 443	32.11 460	49.35 480	38.19 444	84.88 276	66.37 470

SIFT-NN-NCMNet		57.48 410	56.02 425	61.86 379	66.93 423	69.26 89	62.14 398	44.46 509	42.32 429	67.01 406	71.93 444	32.46 456	50.96 469	35.06 480	81.87 337	65.36 481

SIFT-UM-Cal		57.67 407	56.99 412	59.70 411	64.92 452	66.46 120	59.84 429	46.03 500	44.18 402	76.77 203	71.89 445	29.03 494	48.71 485	33.08 496	87.13 233	63.93 493

BH-w/o		64.81 316	64.29 327	66.36 315	76.08 234	54.71 257	65.61 348	75.23 254	50.10 309	71.05 346	71.86 446	54.33 296	79.02 181	38.20 443	76.14 437	65.36 481

EI-MVSNet-Vis-set		72.78 158	71.87 185	75.54 112	74.77 254	59.02 213	72.24 203	71.56 299	63.92 110	78.59 155	71.59 447	66.22 147	78.60 189	67.58 124	80.32 381	89.00 37

UnsupCasMVSNet_bld		50.01 474	51.03 470	46.95 494	58.61 505	32.64 496	48.31 506	53.27 463	34.27 494	60.47 469	71.53 448	41.40 396	47.07 499	30.68 506	60.78 525	61.13 507

thres200		57.55 409	57.02 411	59.17 417	67.89 404	34.93 484	58.91 439	57.25 434	50.24 306	64.01 439	71.46 449	32.49 455	71.39 326	31.31 503	79.57 398	71.19 423

UWE-MVS		52.94 451	52.70 454	53.65 457	73.56 286	27.49 523	57.30 455	49.57 481	38.56 463	62.79 455	71.42 450	19.49 537	60.41 425	24.33 535	77.33 427	73.06 394

EI-MVSNet-UG-set		72.63 162	71.68 190	75.47 113	74.67 256	58.64 221	72.02 209	71.50 300	63.53 116	78.58 157	71.39 451	65.98 149	78.53 190	67.30 134	80.18 385	89.23 31

SIFT-NN		56.62 419	55.34 436	60.47 402	67.01 422	67.25 109	61.74 401	45.38 505	42.69 425	64.49 427	71.36 452	28.48 495	47.55 495	36.68 461	80.23 383	66.63 468

SIFT-NN-PointCN		57.17 415	56.12 423	60.35 407	62.47 473	65.79 129	59.98 426	44.36 510	42.73 424	72.13 320	71.16 453	30.84 477	48.08 493	36.92 459	84.45 290	67.17 461

SIFT-CM-Cal		57.90 405	56.75 415	61.34 389	65.62 439	67.48 106	60.91 413	44.69 506	44.05 403	73.16 299	71.09 454	30.69 480	50.23 475	33.27 494	87.25 221	66.31 471

ETV-MVS		72.72 160	72.16 181	74.38 127	76.90 218	55.95 241	73.34 187	84.67 59	62.04 131	72.19 319	70.81 455	65.90 151	85.24 64	58.64 237	84.96 269	81.95 244

EIA-MVS		68.59 253	67.16 278	72.90 166	75.18 245	55.64 248	69.39 265	81.29 138	52.44 265	64.53 426	70.69 456	60.33 222	82.30 121	54.27 298	76.31 436	80.75 272

blended_shiyan6		62.20 357	61.77 358	63.47 352	67.98 401	40.64 431	60.46 421	69.15 332	47.24 357	66.43 411	70.57 457	43.73 373	71.93 315	43.16 397	87.24 222	77.85 328

blended_shiyan8		62.19 358	61.77 358	63.46 353	68.01 399	40.65 430	60.47 420	69.13 335	47.24 357	66.44 410	70.55 458	43.75 372	71.91 316	43.18 396	87.19 229	77.81 330

EI-MVSNet		69.61 229	69.01 243	71.41 201	73.94 281	49.90 298	71.31 233	71.32 305	58.22 165	75.40 238	70.44 459	58.16 255	75.85 243	62.51 182	79.81 392	88.48 46

CVMVSNet		59.21 392	58.44 397	61.51 384	73.94 281	47.76 332	71.31 233	64.56 383	26.91 527	60.34 470	70.44 459	36.24 433	67.65 374	53.57 306	68.66 498	69.12 444

tpm cat1		54.02 442	52.63 455	58.19 429	64.85 454	39.86 438	66.26 338	57.28 433	32.16 505	56.90 488	70.39 461	32.75 452	65.30 404	34.29 487	58.79 529	69.41 441

myMVS_eth3d28		51.35 464	51.99 461	49.44 483	69.21 375	22.51 540	49.82 503	49.11 484	49.00 331	55.03 501	70.31 462	22.73 523	52.88 464	24.33 535	78.39 416	72.92 396

PMMVS2		37.74 507	40.87 506	28.36 526	42.41 549	5.35 556	24.61 542	27.75 547	32.15 506	47.85 529	70.27 463	35.85 434	29.51 545	19.08 543	67.85 502	50.22 525

EPMVS		45.74 489	46.53 492	43.39 513	54.14 528	22.33 541	55.02 472	35.00 544	34.69 492	51.09 518	70.20 464	25.92 506	42.04 527	37.19 454	55.50 536	65.78 475

WB-MVSnew		53.94 444	54.76 442	51.49 470	71.53 330	28.05 519	58.22 449	50.36 477	37.94 469	59.16 478	70.17 465	49.21 335	51.94 465	24.49 533	71.80 477	74.47 382

testing99		55.16 434	54.56 444	56.98 441	70.13 363	30.58 510	54.55 478	54.11 455	49.53 318	56.76 490	70.14 466	22.76 522	65.79 400	36.99 457	76.04 438	74.57 378

testing91		55.74 428	55.29 437	57.08 439	70.63 345	30.85 508	54.94 475	56.31 447	50.34 304	57.08 486	70.10 467	24.50 514	65.86 398	36.98 458	76.75 432	74.53 380

KD-MVS_2432*1600		52.05 459	51.58 463	53.44 459	52.11 533	31.20 504	44.88 521	64.83 380	41.53 435	64.37 431	70.03 468	15.61 547	64.20 407	36.25 466	74.61 451	64.93 487

miper_refine_blended		52.05 459	51.58 463	53.44 459	52.11 533	31.20 504	44.88 521	64.83 380	41.53 435	64.37 431	70.03 468	15.61 547	64.20 407	36.25 466	74.61 451	64.93 487

our_test_3		56.46 421	56.51 417	56.30 444	67.70 407	39.66 441	55.36 471	52.34 468	40.57 449	63.85 441	69.91 470	40.04 407	58.22 443	43.49 394	75.29 447	71.03 426

xiu_mvs_v2_base		64.43 324	63.96 330	65.85 322	77.72 195	51.32 282	63.63 384	72.31 292	45.06 392	61.70 459	69.66 471	62.56 184	73.93 282	49.06 345	73.91 459	72.31 408

SIFT-PointCN		56.55 420	55.82 428	58.75 422	62.59 470	63.48 158	59.22 432	45.58 502	42.97 423	74.44 268	69.65 472	25.00 512	47.28 498	35.25 477	87.73 204	65.49 478

ArgMatch-Sym		63.94 331	63.05 346	66.61 312	76.68 222	75.81 34	65.98 340	57.57 429	35.60 486	80.60 130	69.62 473	43.62 374	55.74 452	49.14 343	88.61 187	68.29 450

tpmrst		50.15 472	51.38 465	46.45 500	56.05 517	24.77 534	64.40 374	49.98 478	36.14 482	53.32 511	69.59 474	35.16 437	48.69 486	39.24 432	58.51 531	65.89 474

WTY-MVS		49.39 478	50.31 477	46.62 499	61.22 481	32.00 501	46.61 515	49.77 479	33.87 496	54.12 507	69.55 475	41.96 388	45.40 509	31.28 504	64.42 514	62.47 500

SIFT-PCN-Cal		56.03 425	55.47 432	57.69 434	63.19 467	62.93 165	58.63 443	43.46 516	42.37 428	75.62 230	69.51 476	25.32 510	44.67 516	33.77 491	87.41 212	65.45 480

UWE-MVS-28		44.18 498	44.37 503	43.61 512	60.10 490	16.96 547	52.62 489	33.27 545	36.79 477	48.86 526	69.47 477	19.96 536	45.65 505	13.40 545	64.83 512	68.23 451

SIFT-NCMNet		56.27 423	55.94 427	57.26 438	62.54 471	64.28 149	59.61 431	41.26 532	43.43 415	78.50 159	69.35 478	32.26 459	45.98 503	27.16 522	89.34 171	61.53 506

thisisatest0515		60.48 382	57.86 402	68.34 278	67.25 413	46.42 362	60.58 419	62.14 398	40.82 444	63.58 449	69.12 479	26.28 503	78.34 200	48.83 346	82.13 332	80.26 285

patchmatchnet-post											68.99 480	31.32 470	69.38 356

PatchMatch-RL		58.68 397	57.72 403	61.57 383	76.21 230	73.59 52	61.83 399	49.00 487	47.30 356	61.08 464	68.97 481	50.16 325	59.01 434	36.06 472	68.84 497	52.10 521

testing222		53.37 446	52.50 457	55.98 447	70.51 353	29.68 514	56.20 464	51.85 469	46.19 369	56.76 490	68.94 482	19.18 538	65.39 402	25.87 528	76.98 430	72.87 398

MS-PatchMatch		55.59 430	54.89 441	57.68 435	69.18 376	49.05 309	61.00 412	62.93 394	35.98 483	58.36 481	68.93 483	36.71 430	66.59 393	37.62 451	63.30 517	57.39 516

cascas		64.59 320	62.77 351	70.05 237	75.27 243	50.02 295	61.79 400	71.61 297	42.46 427	63.68 446	68.89 484	49.33 333	80.35 160	47.82 361	84.05 301	79.78 292

MVS		60.62 381	59.97 382	62.58 368	68.13 398	47.28 342	68.59 292	73.96 266	32.19 504	59.94 473	68.86 485	50.48 323	77.64 215	41.85 411	75.74 439	62.83 496

PVSNet_Blended		62.90 345	61.64 362	66.69 310	69.81 367	49.36 306	61.23 409	78.96 195	42.04 430	59.98 471	68.86 485	51.82 311	78.20 204	44.30 387	77.77 424	72.52 403

test_fmvs3		56.78 418	55.99 426	59.12 419	53.96 530	48.09 324	58.76 440	66.22 366	27.54 521	76.66 205	68.69 487	25.32 510	51.31 466	53.42 309	73.38 464	77.97 327

MAR-MVS		67.72 268	66.16 296	72.40 183	74.45 265	64.99 139	74.87 158	77.50 223	48.67 336	65.78 417	68.58 488	57.01 275	77.79 212	46.68 370	81.92 335	74.42 383
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
testing11		53.13 448	52.26 459	55.75 448	70.44 354	31.73 502	54.75 476	52.40 467	44.81 395	52.36 514	68.40 489	21.83 526	65.74 401	32.64 499	72.73 468	69.78 435

PS-MVSNAJ		64.27 327	63.73 333	65.90 321	77.82 193	51.42 280	63.33 387	72.33 291	45.09 391	61.60 460	68.04 490	62.39 188	73.95 281	49.07 344	73.87 460	72.34 407

ETVMVS		50.32 471	49.87 479	51.68 468	70.30 359	26.66 526	52.33 492	43.93 512	43.54 413	54.91 502	67.95 491	20.01 535	60.17 428	22.47 538	73.40 463	68.22 452

wanda-best-256-512		61.16 373	60.55 377	62.98 360	66.67 425	39.85 439	58.66 441	68.87 340	46.67 363	64.46 428	67.75 492	41.94 389	71.84 317	42.67 400	87.24 222	77.26 337

FE-blended-shiyan7		61.16 373	60.55 377	62.98 360	66.67 425	39.85 439	58.66 441	68.87 340	46.67 363	64.46 428	67.75 492	41.94 389	71.84 317	42.67 400	87.24 222	77.26 337

usedtu_blend_shiyan5		63.30 339	63.13 344	63.78 344	66.67 425	41.75 414	68.57 294	73.64 267	57.20 181	64.46 428	67.75 492	41.94 389	72.34 304	40.72 423	87.24 222	77.26 337

test0.0.03 1		47.72 484	48.31 483	45.93 501	55.53 522	29.39 515	46.40 516	41.21 533	43.41 416	55.81 497	67.65 495	29.22 491	43.77 521	25.73 530	69.87 491	64.62 489

1112_ss		59.48 390	58.99 391	60.96 395	77.84 192	42.39 409	61.42 407	68.45 351	37.96 468	59.93 474	67.46 496	45.11 362	65.07 405	40.89 419	71.81 476	75.41 366

ab-mvs-re		5.62 516	7.50 519	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	67.46 496	0.00 558	0.00 555	0.00 553	0.00 553	0.00 550

baseline2		55.57 431	52.74 453	64.05 340	65.26 444	44.11 390	62.38 395	54.43 453	39.03 459	51.21 517	67.35 498	33.66 444	72.45 301	37.14 455	64.22 515	75.60 363

1314		59.83 387	58.86 392	62.74 366	65.71 438	44.78 381	68.59 292	72.63 286	33.54 500	61.05 466	67.29 499	43.62 374	71.26 327	49.49 338	67.84 503	72.19 410

gbinet_0.2-2-1-0.02		62.58 352	61.83 357	64.86 332	67.07 418	41.37 416	61.56 404	67.91 354	49.27 322	66.62 409	67.23 500	41.53 395	74.46 271	45.94 378	89.31 172	78.74 309

IB-MVS	49.67 18	59.69 388	56.96 413	67.90 284	68.19 395	50.30 292	61.42 407	65.18 376	47.57 351	55.83 496	67.15 501	23.77 517	79.60 173	43.56 393	79.97 388	73.79 389
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
blend_shiyan4		57.39 412	55.27 438	63.73 346	67.25 413	41.75 414	60.08 425	69.15 332	47.57 351	64.19 436	67.14 502	20.46 531	72.34 304	40.73 422	60.88 524	77.11 342

UBG		49.18 479	49.35 480	48.66 489	70.36 357	26.56 528	50.53 499	45.61 501	37.43 472	53.37 510	65.97 503	23.03 521	54.20 459	26.29 523	71.54 478	65.20 484

sss		47.59 485	48.32 482	45.40 504	56.73 516	33.96 490	45.17 519	48.51 489	32.11 508	52.37 513	65.79 504	40.39 405	41.91 528	31.85 501	61.97 521	60.35 509

dp		44.09 499	44.88 500	41.72 517	58.53 507	23.18 537	54.70 477	42.38 525	34.80 490	44.25 540	65.61 505	24.48 515	44.80 513	29.77 511	49.42 540	57.18 517

test_fmvs2		54.80 436	54.11 447	56.88 442	51.76 535	49.95 297	56.70 458	65.80 369	26.22 528	69.42 369	65.25 506	31.82 466	49.98 477	49.63 336	70.36 487	70.71 427

PVSNet	43.83 21	51.56 462	51.17 467	52.73 462	68.34 391	38.27 453	48.22 507	53.56 460	36.41 479	54.29 506	64.94 507	34.60 439	54.20 459	30.34 507	69.87 491	65.71 476

Syy-MVS		54.13 439	55.45 433	50.18 476	68.77 383	23.59 536	55.02 472	44.55 507	43.80 406	58.05 483	64.07 508	46.22 355	58.83 435	46.16 376	72.36 471	68.12 454

myMVS_eth3d		50.36 470	50.52 475	49.88 477	68.77 383	22.69 538	55.02 472	44.55 507	43.80 406	58.05 483	64.07 508	14.16 549	58.83 435	33.90 490	72.36 471	68.12 454

pmmvs3		46.71 486	45.09 497	51.55 469	56.76 515	48.25 320	55.78 468	39.53 538	24.13 535	50.35 522	63.40 510	15.90 546	51.08 468	29.29 514	70.69 486	55.33 519

test_f		43.79 500	45.63 493	38.24 523	42.29 550	38.58 450	34.76 539	47.68 493	22.22 541	67.34 402	63.15 511	31.82 466	30.60 543	39.19 433	62.28 520	45.53 535

MASt3R-SfM		45.75 488	47.16 489	41.50 518	47.00 542	47.91 329	45.50 518	38.10 539	21.81 543	73.91 284	62.86 512	29.14 493	29.95 544	34.59 484	71.54 478	46.65 530

test_vis3_rt		51.94 461	51.04 469	54.65 452	46.32 544	50.13 294	44.34 523	78.17 213	23.62 536	68.95 376	62.81 513	21.41 527	38.52 537	41.49 413	72.22 473	75.30 369

gm-plane-assit					62.51 472	33.91 492			37.25 474		62.71 514		72.74 292	38.70 436

MVE	27.91 23	36.69 509	35.64 512	39.84 520	43.37 548	35.85 478	19.49 543	24.61 549	24.68 533	39.05 544	62.63 515	38.67 418	27.10 547	21.04 541	47.25 542	56.56 518
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
mvsany_test3		43.76 501	41.01 505	52.01 466	48.09 540	57.74 228	42.47 525	23.85 551	23.30 538	64.80 425	62.17 516	27.12 498	40.59 532	29.17 516	48.11 541	57.69 515

new_pmnet		37.55 508	39.80 509	30.79 525	56.83 514	16.46 548	39.35 532	30.65 546	25.59 531	45.26 534	61.60 517	24.54 513	28.02 546	21.60 539	52.80 539	47.90 527

dmvs_re		49.91 475	50.77 473	47.34 492	59.98 492	38.86 448	53.18 484	53.58 459	39.75 452	55.06 500	61.58 518	36.42 432	44.40 517	29.15 517	68.23 499	58.75 513

test_cas_vis1_n_1920		50.90 467	50.92 471	50.83 474	54.12 529	47.80 330	51.44 495	54.61 452	26.95 526	63.95 440	60.85 519	37.86 425	44.97 512	45.53 382	62.97 518	59.72 511

test_vis1_n_1920		52.96 450	53.50 449	51.32 471	59.15 501	44.90 378	56.13 465	64.29 386	30.56 514	59.87 475	60.68 520	40.16 406	47.47 496	48.25 356	62.46 519	61.58 505

test_fmvs1_n		52.70 453	52.01 460	54.76 451	53.83 531	50.36 290	55.80 467	65.90 368	24.96 532	65.39 418	60.64 521	27.69 497	48.46 489	45.88 380	67.99 501	65.46 479

test-LLR		50.43 469	50.69 474	49.64 480	60.76 484	41.87 411	53.18 484	45.48 503	43.41 416	49.41 524	60.47 522	29.22 491	44.73 514	42.09 408	72.14 474	62.33 503

test-mter		48.56 482	48.20 485	49.64 480	60.76 484	41.87 411	53.18 484	45.48 503	31.91 509	49.41 524	60.47 522	18.34 540	44.73 514	42.09 408	72.14 474	62.33 503

XFeat-MNN		48.68 481	49.35 480	46.65 498	44.49 546	46.89 351	46.91 513	43.80 513	27.16 524	75.21 245	60.05 524	22.65 524	46.52 500	39.33 430	84.57 288	46.53 531

test_fmvs1		51.51 463	50.86 472	53.48 458	49.72 538	49.35 308	54.11 479	64.96 378	24.64 534	63.66 447	59.61 525	28.33 496	48.45 490	45.38 385	67.30 506	62.66 499

test_vis1_n		51.27 465	50.41 476	53.83 455	56.99 513	50.01 296	56.75 457	60.53 410	25.68 530	59.74 476	57.86 526	29.40 490	47.41 497	43.10 398	63.66 516	64.08 492

dmvs_testset		45.26 491	47.51 486	38.49 522	59.96 494	14.71 549	58.50 447	43.39 517	41.30 437	51.79 516	56.48 527	39.44 414	49.91 479	21.42 540	55.35 538	50.85 523

TESTMET0.1,1		45.17 492	44.93 498	45.89 502	56.02 518	38.31 452	53.18 484	41.94 528	27.85 520	44.86 537	56.47 528	17.93 542	41.50 531	38.08 446	68.06 500	57.85 514

XFeat-NN		44.60 497	44.89 499	43.74 511	46.61 543	44.56 383	41.07 527	40.59 536	23.40 537	66.73 408	54.97 529	20.65 529	40.41 533	33.52 493	76.49 433	46.25 532

CHOSEN 280x420		41.62 503	39.89 508	46.80 496	61.81 477	51.59 278	33.56 540	35.74 543	27.48 522	37.64 547	53.53 530	23.24 519	42.09 526	27.39 521	58.64 530	46.72 529

mvsany_test1		37.88 506	35.74 511	44.28 508	47.28 541	49.90 298	36.54 537	24.37 550	19.56 544	45.76 532	53.46 531	32.99 449	37.97 538	26.17 524	35.52 544	44.99 536

PMMVS		44.69 494	43.95 504	46.92 495	50.05 537	53.47 268	48.08 509	42.40 524	22.36 540	44.01 541	53.05 532	42.60 386	45.49 507	31.69 502	61.36 523	41.79 537

GG-mvs-BLEND				52.24 464	60.64 487	29.21 517	69.73 259	42.41 523		45.47 533	52.33 533	20.43 532	68.16 369	25.52 531	65.42 511	59.36 512

E-PMN		45.17 492	45.36 495	44.60 507	50.07 536	42.75 405	38.66 533	42.29 526	46.39 367	39.55 543	51.15 534	26.00 505	45.37 510	37.68 449	76.41 434	45.69 534

test_vis1_rt		46.70 487	45.24 496	51.06 473	44.58 545	51.04 285	39.91 531	67.56 356	21.84 542	51.94 515	50.79 535	33.83 442	39.77 534	35.25 477	61.50 522	62.38 501

PDCNetPlus		38.77 505	39.67 510	36.07 524	38.82 552	27.82 522	36.52 538	51.55 473	22.53 539	37.81 546	50.69 536	7.16 555	32.98 541	28.21 519	83.73 309	47.40 528

0.4-1-1-0.1		51.02 466	48.31 483	59.15 418	60.95 483	37.94 460	53.17 488	59.12 422	39.52 453	47.88 528	50.31 537	20.36 533	69.99 347	35.79 473	67.66 505	69.51 440

PVSNet_0	36.71 22	41.12 504	40.78 507	42.14 514	59.97 493	40.13 435	40.97 528	42.24 527	30.81 513	44.86 537	49.41 538	40.70 403	45.12 511	23.15 537	34.96 545	41.16 539

EMVS		44.61 496	44.45 502	45.10 506	48.91 539	43.00 403	37.92 534	41.10 534	46.75 362	38.00 545	48.43 539	26.42 501	46.27 502	37.11 456	75.38 445	46.03 533

0.3-1-1-0.015		49.68 476	46.67 490	58.69 424	58.94 503	37.51 465	51.35 496	59.18 420	38.35 464	44.62 539	47.14 540	18.49 539	69.68 352	35.13 479	66.84 508	68.87 446

0.4-1-1-0.2		49.48 477	46.57 491	58.21 428	58.02 510	36.93 467	50.24 501	59.18 420	37.97 467	44.94 535	46.16 541	20.52 530	69.54 354	34.84 482	67.28 507	68.17 453

dongtai		31.66 510	32.98 513	27.71 527	58.58 506	12.61 551	45.02 520	14.24 555	41.90 432	47.93 527	43.91 542	10.65 552	41.81 530	14.06 544	20.53 548	28.72 543

test_method		19.26 513	19.12 517	19.71 529	9.09 555	1.91 558	7.79 545	53.44 461	1.42 548	10.27 551	35.80 543	17.42 544	25.11 548	12.44 546	24.38 547	32.10 542

GLUNet-SfM		24.03 511	24.76 514	21.84 528	12.84 554	18.20 545	27.35 541	15.92 553	9.48 546	63.07 454	34.11 544	10.20 553	23.13 549	9.60 549	40.26 543	24.18 544

kuosan		22.02 512	23.52 516	17.54 530	41.56 551	11.24 552	41.99 526	13.39 556	26.13 529	28.87 548	30.75 545	9.72 554	21.94 550	4.77 550	14.49 549	19.43 545

DeepMVS_CX				11.83 531	15.51 553	13.86 550		11.25 557	5.76 547	20.85 550	26.46 546	17.06 545	9.22 551	9.69 548	13.82 550	12.42 546

X-MVStestdata		76.81 87	74.79 111	82.85 8	89.43 15	77.61 19	86.80 20	84.66 60	72.71 32	82.87 95	9.95 547	73.86 60	86.31 22	78.84 23	94.03 60	84.64 142

tmp_tt		11.98 515	14.73 518	3.72 532	2.28 556	4.62 557	19.44 544	14.50 554	0.47 550	21.55 549	9.58 548	25.78 507	4.57 552	11.61 547	27.37 546	1.96 547

test_post1							66.63 331				2.08 549	30.66 481	59.33 432	40.34 426

test_post											1.99 550	30.91 476	54.76 457

test123		4.43 518	5.78 521	0.39 534	0.97 557	0.28 559	46.33 517	0.45 558	0.31 551	0.62 553	1.50 551	0.61 557	0.11 554	0.56 551	0.63 551	0.77 549

testmvs		4.06 519	5.28 522	0.41 533	0.64 558	0.16 560	42.54 524	0.31 559	0.26 552	0.50 554	1.40 552	0.77 556	0.17 553	0.56 551	0.55 552	0.90 548

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

pcd_1.5k_mvsjas		5.20 517	6.93 520	0.00 535	0.00 559	0.00 561	0.00 546	0.00 560	0.00 553	0.00 555	0.00 553	62.39 188	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

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

test-260524					85.04 77	63.52 157		84.79 52		83.97 83		74.92 52	85.60 53	74.59 56	93.74 67

WAC-MVS						22.69 538								36.10 470

FOURS1					89.19 23	77.84 17	91.64 1	89.11 2	84.05 2	91.57 2

MSC_two_6792asdad				79.02 57	83.14 106	67.03 113		80.75 152					86.24 26	77.27 38	94.85 30	83.78 175

No_MVS				79.02 57	83.14 106	67.03 113		80.75 152					86.24 26	77.27 38	94.85 30	83.78 175

eth-test2					0.00 559

eth-test					0.00 559

IU-MVS					86.12 56	60.90 187		80.38 164	45.49 379	81.31 119				75.64 46	94.39 45	84.65 141

save fliter					87.00 39	67.23 111	79.24 97	77.94 218	56.65 191

test_0728_SECOND				76.57 95	86.20 51	60.57 192	83.77 49	85.49 33					85.90 42	75.86 43	94.39 45	83.25 196

GSMVS																70.05 431

test_part2					85.90 62	66.44 121				84.61 75

sam_mvs1												31.41 469				70.05 431

sam_mvs												31.21 473

MTGPA								80.63 158

MTMP							84.83 38	19.26 552

test9_res														72.12 86	91.37 106	77.40 333

agg_prior2														70.70 95	90.93 125	78.55 313

agg_prior					84.44 89	66.02 127		78.62 206		76.95 193			80.34 161

test_prior4						70.14 78	77.57 115

test_prior				75.27 117	82.15 126	59.85 201		84.33 73					83.39 98			82.58 224

旧先验2							71.17 236		45.11 390	78.54 158			61.28 423	59.19 230

新几何2							71.33 232

无先验							74.82 159	70.94 315	47.75 350				76.85 235	54.47 293		72.09 411

原ACMM2							74.78 163

testdata2													67.30 379	48.34 354

segment_acmp												68.30 118

testdata1							68.34 300		57.24 180

test12				76.51 96	82.28 123	60.94 186		81.64 129		73.60 289		64.88 164	85.19 67		90.42 139	83.38 192

plane_prior7					85.18 72	66.21 124

plane_prior6					84.18 93	65.31 135						60.83 214

plane_prior5								85.49 33					86.15 31	71.09 90	90.94 123	84.82 134

plane_prior3						65.67 130			63.82 112	78.23 163

plane_prior2							82.74 61		65.45 89

plane_prior1					84.46 88

plane_prior						65.18 136	80.06 89		61.88 133						89.91 155

n2								0.00 560

nn								0.00 560

door-mid								55.02 450

test11								82.71 106

door								52.91 465

HQP5-MVS						58.80 217

HQP-NCC					82.37 120		77.32 120		59.08 153	71.58 334

ACMP_Plane					82.37 120		77.32 120		59.08 153	71.58 334

BP-MVS														67.38 131

HQP4-MVS										71.59 332			85.31 59			83.74 177

HQP3-MVS								84.12 79							89.16 173

HQP2-MVS												58.09 258

MDTV_nov1_ep13_2view						18.41 544	53.74 481		31.57 510	44.89 536		29.90 488		32.93 497		71.48 416

ACMMP++_ref															89.47 166

ACMMP++															91.96 95

Test By Simon												62.56 184

High-resolution multi-view benchmark