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 76	68.08 117	97.05 1	96.93 1

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 73	74.51 59	96.15 2	92.88 7

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 36	74.35 61	96.11 3	85.81 99
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
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	82.44 115	64.82 152	96.10 4	87.21 63

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 27	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 27	77.13 40	95.96 5	86.08 92

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	80.52 158	74.27 62	95.73 7	80.98 264
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
NR-MVSNet		73.62 127	74.05 131	72.33 184	83.50 101	43.71 395	65.65 348	77.32 225	64.32 107	75.59 230	87.08 147	62.45 187	81.34 136	54.90 286	95.63 8	91.93 8

WR-MVS_H		80.22 57	82.17 48	74.39 125	89.46 14	42.69 407	78.24 109	82.24 118	78.21 12	89.57 9	92.10 20	68.05 122	85.59 53	66.04 142	95.62 9	94.88 5

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	75.21 244	84.02 234	52.85 305	81.82 128	61.45 194	95.50 10	86.24 87

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	82.92 105	81.59 3	95.50 10	85.56 108

TranMVSNet+NR-MVSNet		76.13 92	77.66 83	71.56 196	84.61 85	42.57 409	70.98 237	78.29 211	68.67 65	83.04 91	89.26 95	72.99 66	80.75 153	55.58 277	95.47 12	91.35 11

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 47	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
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 29	79.24 21	95.36 14	82.49 226

Baseline_NR-MVSNet		70.62 206	73.19 152	62.92 366	76.97 210	34.44 489	68.84 282	70.88 316	60.25 146	79.50 142	90.53 59	61.82 198	69.11 359	54.67 290	95.27 15	85.22 115

UniMVSNet (Re)		75.00 109	75.48 105	73.56 143	83.14 106	47.92 327	70.41 247	81.04 147	63.67 114	79.54 140	86.37 181	62.83 181	81.82 128	57.10 257	95.25 16	90.94 15

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 33	79.90 9	95.21 17	82.72 218

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 33	79.90 9	95.21 17	82.72 218

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 40	80.47 8	95.20 19	82.10 236

PS-CasMVS		80.41 54	82.86 41	73.07 155	89.93 6	39.21 444	77.15 124	81.28 138	79.74 5	90.87 4	92.73 13	75.03 50	84.93 69	63.83 168	95.19 20	95.07 3

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 46	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
PEN-MVS		80.46 53	82.91 39	73.11 153	89.83 8	39.02 448	77.06 126	82.61 108	80.04 4	90.60 6	92.85 11	74.93 51	85.21 64	63.15 178	95.15 22	95.09 2

CP-MVSNet		79.48 61	81.65 52	72.98 159	89.66 12	39.06 447	76.76 127	80.46 161	78.91 8	90.32 7	91.70 32	68.49 115	84.89 70	63.40 175	95.12 23	95.01 4

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.
UniMVSNet_NR-MVSNet		74.90 112	75.65 102	72.64 176	83.04 111	45.79 368	69.26 270	78.81 197	66.66 79	81.74 113	86.88 154	63.26 175	81.07 144	56.21 267	94.98 25	91.05 13

DU-MVS		74.91 111	75.57 104	72.93 163	83.50 101	45.79 368	69.47 264	80.14 168	65.22 95	81.74 113	87.08 147	61.82 198	81.07 144	56.21 267	94.98 25	91.93 8

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 75	83.30 1	94.96 27	86.17 91
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
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
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 65	79.45 16	94.91 29	88.15 52

MSC_two_6792asdad				79.02 57	83.14 106	67.03 113		80.75 151					86.24 25	77.27 38	94.85 30	83.78 174

No_MVS				79.02 57	83.14 106	67.03 113		80.75 151					86.24 25	77.27 38	94.85 30	83.78 174

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 74	78.41 25	94.78 32	82.74 217
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTAPA		83.19 22	83.87 23	81.13 33	91.16 2	78.16 15	84.87 37	80.63 157	72.08 44	84.93 68	90.79 51	74.65 54	84.42 79	80.98 5	94.75 33	80.82 268

test_0728_THIRD									74.03 24	85.83 52	90.41 65	75.58 43	85.69 49	77.43 35	94.74 34	84.31 160

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

DTE-MVSNet		80.35 55	82.89 40	72.74 173	89.84 7	37.34 468	77.16 123	81.81 126	80.45 3	90.92 3	92.95 9	74.57 55	86.12 32	63.65 171	94.68 36	94.76 6

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 70	79.30 20	94.63 37	82.35 229

FC-MVSNet-test		73.32 139	74.78 112	68.93 265	79.21 166	36.57 471	71.82 222	79.54 185	57.63 176	82.57 101	90.38 70	59.38 238	78.99 181	57.91 247	94.56 38	91.23 12

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
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 54	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

UA-Net		81.56 39	82.28 47	79.40 51	88.91 28	69.16 90	84.67 40	80.01 171	75.34 18	79.80 137	94.91 2	69.79 104	80.25 162	72.63 79	94.46 40	88.78 44

ACMH	63.62 14	77.50 82	80.11 61	69.68 244	79.61 158	56.28 238	78.81 101	83.62 86	63.41 120	87.14 35	90.23 77	76.11 38	73.32 288	67.58 124	94.44 43	79.44 297
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
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

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 43	75.29 47	94.39 45	83.08 203

IU-MVS					86.12 56	60.90 187		80.38 163	45.49 380	81.31 119				75.64 46	94.39 45	84.65 141

DVP-MVS		81.15 44	83.12 37	75.24 117	86.16 54	60.78 189	83.77 49	80.58 159	72.48 37	85.83 52	90.41 65	78.57 19	85.69 49	75.86 43	94.39 45	79.24 300
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				76.57 95	86.20 51	60.57 192	83.77 49	85.49 33					85.90 41	75.86 43	94.39 45	83.25 195

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
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 39	82.00 2	94.36 49	83.35 193

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 77	77.73 32	94.34 51	85.93 97

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	83.47 185
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
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

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 24	79.41 18	94.25 54	83.95 169

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 37	79.58 14	94.23 55	82.82 214

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 56	78.23 26	94.22 56	84.86 130

test_241102_TWO								84.80 51	72.61 35	84.93 68	89.70 88	77.73 25	85.89 43	75.29 47	94.22 56	83.25 195

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 45	74.09 63	94.20 58	84.73 138

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

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	9.95 551	73.86 60	86.31 22	78.84 23	94.03 60	84.64 142

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	82.62 222
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
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

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	81.75 132	73.75 69	93.78 64

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 99	76.01 42	93.77 65	84.81 136

IS-MVSNet		75.10 106	75.42 106	74.15 130	79.23 165	48.05 325	79.43 94	78.04 215	70.09 58	79.17 146	88.02 134	53.04 304	83.60 90	58.05 246	93.76 66	90.79 17

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

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

ALIKED-MNN		63.44 335	63.42 338	63.48 351	73.99 278	70.97 69	71.80 223	66.48 364	32.46 505	71.87 324	81.60 301	36.54 431	58.50 440	42.45 403	93.63 69	60.97 510

PMVS	70.70 6	81.70 38	83.15 36	77.36 87	90.35 5	82.82 2	82.15 64	79.22 191	74.08 23	87.16 34	91.97 22	84.80 2	76.97 228	64.98 150	93.61 70	72.28 410
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
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 37	77.77 31	93.58 71	83.09 202

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 95	74.03 67	93.57 72	84.35 159
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
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	80.55 157	72.51 81	93.37 73	83.48 184

FIs		72.56 164	73.80 135	68.84 268	78.74 180	37.74 463	71.02 236	79.83 174	56.12 195	80.88 128	89.45 92	58.18 254	78.28 201	56.63 261	93.36 74	90.51 19

WR-MVS		71.20 193	72.48 172	67.36 294	84.98 78	35.70 481	64.43 374	68.66 348	65.05 99	81.49 117	86.43 180	57.57 266	76.48 238	50.36 329	93.32 75	89.90 22

CLD-MVS		72.88 155	72.36 176	74.43 124	77.03 207	54.30 259	68.77 289	83.43 89	52.12 271	76.79 201	74.44 411	69.54 106	83.91 83	55.88 270	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
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	82.39 117	74.80 50	93.04 77	81.14 258

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	81.14 258
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ZD-MVS					83.91 95	69.36 86		81.09 145	58.91 159	82.73 99	89.11 102	75.77 41	86.63 13	72.73 78	92.93 79

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	82.60 112	70.08 100	92.80 80	89.25 30

Anonymous20231211		75.54 99	77.19 89	70.59 212	77.67 196	45.70 372	74.73 163	80.19 166	68.80 62	82.95 94	92.91 10	66.26 146	76.76 235	58.41 242	92.77 81	89.30 27

test_prior2							75.57 150		58.92 158	76.53 212	86.78 162	67.83 128		69.81 103	92.76 82

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	77.68 174	87.18 145	69.98 100	85.37 56	68.01 119	92.72 83	85.08 123

EPP-MVSNet		73.86 125	73.38 147	75.31 114	78.19 185	53.35 268	80.45 79	77.32 225	65.11 98	76.47 215	86.80 159	49.47 331	83.77 87	53.89 301	92.72 83	88.81 43

RoMa-HiRes		73.61 128	73.51 143	73.92 133	82.27 124	81.71 3	77.59 114	64.83 380	51.32 287	88.72 16	83.92 239	60.47 219	61.70 422	60.01 218	92.44 85	78.34 314

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	86.65 171	71.46 82	83.53 93	67.95 121	92.44 85	89.60 24

tt0805		76.12 93	78.43 76	69.20 254	81.32 137	41.37 417	76.72 128	77.64 220	63.78 113	82.06 105	87.88 137	79.78 11	79.05 179	64.33 160	92.40 87	87.17 67

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	86.27 183	71.68 76	83.45 96	62.45 184	92.40 87	78.92 307

nrg030		74.87 114	75.99 100	71.52 197	74.90 248	49.88 303	74.10 176	82.58 109	54.55 224	83.50 89	89.21 97	71.51 81	75.74 247	61.24 198	92.34 89	88.94 39

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	87.07 149	74.02 59	80.97 148	77.70 33	92.32 90	80.62 276
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
DKM		69.82 224	69.29 234	71.40 201	80.33 148	80.76 8	73.05 190	60.16 415	47.00 358	85.42 63	79.91 335	48.29 347	58.24 443	57.18 254	92.25 91	75.19 372

Anonymous20240521		63.55 333	66.07 298	55.99 447	66.18 434	44.04 392	68.77 289	68.80 345	46.99 359	72.57 310	85.84 199	39.87 408	50.22 478	53.40 309	92.23 92	73.71 391

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	81.53 134	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
tt0320-xc		71.50 186	73.63 140	65.08 329	79.77 156	40.46 434	64.80 364	68.86 342	67.08 73	76.84 198	93.24 6	70.33 95	66.77 392	49.76 333	92.02 94	88.02 53

ACMMP++															91.96 95

v7n		79.37 63	80.41 59	76.28 100	78.67 181	55.81 244	79.22 98	82.51 112	70.72 53	87.54 26	92.44 16	68.00 124	81.34 136	72.84 77	91.72 96	91.69 10

VDDNet		71.60 184	73.13 154	67.02 304	86.29 47	41.11 420	69.97 254	66.50 363	68.72 64	74.74 255	91.70 32	59.90 228	75.81 244	48.58 351	91.72 96	84.15 165

UniMVSNet_ETH3D		76.74 88	79.02 68	69.92 240	89.27 19	43.81 394	74.47 169	71.70 295	72.33 43	85.50 61	93.65 3	77.98 24	76.88 232	54.60 291	91.64 98	89.08 34

wuyk23d		61.97 360	66.25 293	49.12 488	58.19 510	60.77 191	66.32 338	52.97 465	55.93 203	90.62 5	86.91 153	73.07 65	35.98 541	20.63 545	91.63 99	50.62 527

CNVR-MVS		78.49 71	78.59 73	78.16 74	85.86 65	67.40 107	78.12 112	81.50 131	63.92 110	77.51 177	86.56 175	68.43 117	84.82 72	73.83 68	91.61 100	82.26 233

train_agg		76.38 90	76.55 94	75.86 106	85.47 69	69.32 87	76.42 135	78.69 202	54.00 240	76.97 190	86.74 164	66.60 142	81.10 142	72.50 82	91.56 101	77.15 340

Gipuma		69.55 229	72.83 163	59.70 412	63.63 466	53.97 262	80.08 88	75.93 246	64.24 108	73.49 291	88.93 109	57.89 264	62.46 416	59.75 224	91.55 102	62.67 499
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ALIKED-LG		64.85 314	64.54 322	65.79 323	74.03 277	74.67 42	73.55 181	67.52 357	36.17 483	78.83 151	83.08 267	34.08 440	59.10 434	42.05 410	91.51 103	63.61 495

SixPastTwentyTwo		75.77 94	76.34 95	74.06 131	81.69 132	54.84 255	76.47 131	75.49 250	64.10 109	87.73 22	92.24 19	50.45 324	81.30 138	67.41 127	91.46 104	86.04 94

sc_t1		72.50 168	74.23 126	67.33 295	80.05 152	46.99 350	66.58 334	69.48 328	66.28 82	77.62 176	91.83 29	70.98 90	68.62 365	53.86 303	91.40 105	86.37 86

test9_res														72.12 86	91.37 106	77.40 332

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

ALIKED-NN		61.86 362	61.18 367	63.92 342	71.72 327	71.04 66	69.24 271	66.41 365	29.80 519	64.25 433	81.10 308	35.56 436	58.35 441	41.25 415	91.30 108	62.35 504

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	85.31 207	68.56 112	87.03 11	67.39 129	91.26 109	83.50 181

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 61	66.15 139	91.24 110	87.61 58

DKM-HiRes		70.49 208	69.89 221	72.31 185	81.51 134	80.92 7	73.23 188	58.80 424	49.23 323	84.44 78	81.39 303	49.91 327	61.22 425	59.28 229	91.22 111	74.79 375

HPM-MVS++		79.89 58	79.80 64	80.18 42	89.02 25	78.44 14	83.49 54	80.18 167	64.71 105	78.11 165	88.39 122	65.46 157	83.14 100	77.64 34	91.20 112	78.94 306

KD-MVS_self_test		66.38 292	67.51 269	62.97 364	61.76 479	34.39 490	58.11 452	75.30 251	50.84 295	77.12 189	85.42 202	56.84 276	69.44 356	51.07 322	91.16 113	85.08 123

test_djsdf		78.88 66	78.27 77	80.70 38	81.42 135	71.24 65	83.98 45	75.72 248	52.27 267	87.37 31	92.25 18	68.04 123	80.56 155	72.28 84	91.15 114	90.32 20

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	74.88 254	85.32 206	65.54 155	87.79 2	65.61 147	91.14 115	83.35 193
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testf1		75.66 97	76.57 92	72.95 160	67.07 419	67.62 103	76.10 143	80.68 154	64.95 100	86.58 41	90.94 46	71.20 87	71.68 323	60.46 208	91.13 116	79.56 293

APD_test2		75.66 97	76.57 92	72.95 160	67.07 419	67.62 103	76.10 143	80.68 154	64.95 100	86.58 41	90.94 46	71.20 87	71.68 323	60.46 208	91.13 116	79.56 293

ambc				70.10 234	77.74 194	50.21 293	74.28 174	77.93 218		79.26 144	88.29 127	54.11 298	79.77 169	64.43 158	91.10 118	80.30 283

tt0320		71.34 191	73.47 144	64.97 331	79.92 154	40.81 425	65.22 356	69.07 336	66.72 78	76.15 222	93.36 4	70.35 94	66.90 385	49.31 341	91.09 119	87.21 63

原ACMM1				73.90 134	85.90 62	65.15 138		81.67 128	50.97 292	74.25 271	86.16 188	61.60 201	83.54 92	56.75 260	91.08 120	73.00 396

114514_t		73.40 137	73.33 151	73.64 138	84.15 94	57.11 234	78.20 110	80.02 170	43.76 409	72.55 311	86.07 195	64.00 171	83.35 98	60.14 215	91.03 121	80.45 280

RoMa-SfM		70.84 201	70.47 215	71.95 192	80.95 141	81.09 6	76.44 134	62.08 401	46.25 368	87.14 35	80.63 319	55.60 287	58.69 438	54.19 298	90.98 122	76.07 360

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	78.23 162	89.11 102	60.83 214	86.15 30	71.09 90	90.94 123	84.82 134

plane_prior5								85.49 33					86.15 30	71.09 90	90.94 123	84.82 134

agg_prior2														70.70 95	90.93 125	78.55 312

PHI-MVS		74.92 110	74.36 123	76.61 94	76.40 226	62.32 168	80.38 81	83.15 92	54.16 237	73.23 296	80.75 316	62.19 193	83.86 84	68.02 118	90.92 126	83.65 178

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	78.43 195	55.60 274	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	78.43 195	55.60 274	90.90 127	85.81 99

NCCC		78.25 74	78.04 80	78.89 61	85.61 67	69.45 83	79.80 93	80.99 149	65.77 85	75.55 231	86.25 185	67.42 129	85.42 55	70.10 99	90.88 129	81.81 247

VPNet		65.58 304	67.56 268	59.65 414	79.72 157	30.17 513	60.27 424	62.14 399	54.19 236	71.24 342	86.63 172	58.80 247	67.62 376	44.17 390	90.87 130	81.18 257

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 41	77.43 35	90.78 131	83.49 182

PC_three_1452									46.98 360	81.83 110	86.28 182	66.55 144	84.47 78	63.31 177	90.78 131	83.49 182

h-mvs33		73.08 144	71.61 194	77.48 84	83.89 97	72.89 57	70.47 245	71.12 313	54.28 231	77.89 166	83.41 248	49.04 337	80.98 147	63.62 172	90.77 133	78.58 311

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	78.37 198	74.80 50	90.76 134	82.40 228

PS-MVSNAJss		77.54 79	77.35 88	78.13 76	84.88 79	66.37 122	78.55 104	79.59 183	53.48 252	86.29 45	92.43 17	62.39 188	80.25 162	67.90 122	90.61 135	87.77 55

anonymousdsp		78.60 68	77.80 81	81.00 34	78.01 190	74.34 46	80.09 87	76.12 243	50.51 301	89.19 10	90.88 48	71.45 83	77.78 212	73.38 71	90.60 136	90.90 16

DenseAffine		67.25 277	66.08 296	70.76 209	80.22 150	77.51 25	70.65 243	58.59 426	45.98 373	81.51 116	76.48 388	41.58 394	62.36 417	49.23 342	90.48 137	72.40 407

pmmvs6		71.82 180	73.66 138	66.31 316	75.94 235	42.01 411	66.99 326	72.53 287	63.45 118	76.43 216	92.78 12	72.95 68	69.69 352	51.41 319	90.46 138	87.22 62

test12				76.51 96	82.28 123	60.94 186		81.64 129		73.60 288		64.88 164	85.19 66		90.42 139	83.38 191

ELoFTR		57.63 409	59.55 386	51.85 469	66.16 435	61.46 176	69.66 260	43.94 513	30.20 518	82.28 103	77.47 380	33.76 443	42.30 527	42.10 407	90.40 140	51.81 525

usedtu_dtu_shiyan2		62.25 356	62.27 355	62.18 374	77.08 205	52.84 271	62.56 395	56.33 447	52.43 266	64.22 434	83.26 257	48.47 346	58.06 447	25.75 532	90.34 141	75.64 363

VDD-MVS		70.81 203	71.44 198	68.91 266	79.07 173	46.51 360	67.82 307	70.83 317	61.23 136	74.07 276	88.69 114	59.86 229	75.62 249	51.11 321	90.28 142	84.61 145

mvs_tets		78.93 65	78.67 72	79.72 46	84.81 81	73.93 48	80.65 77	76.50 236	51.98 274	87.40 28	91.86 28	76.09 39	78.53 189	68.58 112	90.20 143	86.69 75

EPNet		69.10 240	67.32 274	74.46 121	68.33 393	61.27 180	77.56 116	63.57 390	60.95 140	56.62 493	82.75 269	51.53 315	81.24 139	54.36 296	90.20 143	80.88 267
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
VPA-MVSNet		68.71 248	70.37 216	63.72 347	76.13 230	38.06 459	64.10 378	71.48 301	56.60 192	74.10 274	88.31 126	64.78 166	69.72 351	47.69 362	90.15 145	83.37 192

TAPA-MVS	65.27 12	75.16 105	74.29 125	77.77 82	74.86 249	68.08 97	77.89 113	84.04 82	55.15 211	76.19 221	83.39 249	66.91 135	80.11 166	60.04 217	90.14 146	85.13 119
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
jajsoiax		78.51 70	78.16 79	79.59 48	84.65 84	73.83 50	80.42 80	76.12 243	51.33 285	87.19 33	91.51 36	73.79 62	78.44 194	68.27 115	90.13 147	86.49 83

PMatch-Up-SfM		68.45 253	66.90 285	73.11 153	77.17 203	76.10 32	71.60 226	62.67 396	47.32 354	87.78 19	82.41 278	24.19 518	66.58 395	58.86 235	90.11 148	76.66 347

Casviewmamba		77.76 77	78.57 74	75.31 114	76.72 220	53.06 269	76.28 141	85.90 26	62.98 125	81.96 107	88.90 110	75.35 46	82.88 107	68.97 109	90.11 148	89.98 21

Anonymous20240529		72.56 164	73.79 136	68.86 267	76.89 218	45.21 376	68.80 288	77.25 227	67.16 72	76.89 194	90.44 62	65.95 150	74.19 276	50.75 324	90.00 150	87.18 66

AdaColmap		74.22 118	74.56 115	73.20 149	81.95 128	60.97 185	79.43 94	80.90 150	65.57 87	72.54 312	81.76 295	70.98 90	85.26 61	47.88 360	90.00 150	73.37 392

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	75.21 244	84.02 234	52.85 305	81.82 128	61.45 194	89.99 152	80.47 279

DP-MVS Recon		73.57 130	72.69 165	76.23 101	82.85 115	63.39 159	74.32 171	82.96 99	57.75 171	70.35 351	81.98 288	64.34 170	84.41 80	49.69 334	89.95 153	80.89 266

test1111		64.62 319	65.19 311	62.93 365	79.01 174	29.91 515	65.45 352	54.41 455	54.09 238	71.47 340	88.48 120	37.02 428	74.29 275	46.83 369	89.94 154	84.58 148

plane_prior						65.18 136	80.06 89		61.88 133						89.91 155

PMatch-SfM		67.96 263	66.40 291	72.63 177	78.06 188	75.26 38	71.85 219	59.63 417	46.07 370	86.78 37	82.02 285	26.32 503	66.37 397	57.00 258	89.87 156	76.27 356

cl____		68.26 261	68.26 255	68.29 278	64.98 451	43.67 396	65.89 343	74.67 258	50.04 309	76.86 196	82.42 277	48.74 341	75.38 250	60.92 203	89.81 157	85.80 103

DIV-MVS_self_test		68.27 259	68.26 255	68.29 278	64.98 451	43.67 396	65.89 343	74.67 258	50.04 309	76.86 196	82.43 276	48.74 341	75.38 250	60.94 202	89.81 157	85.81 99

OPU-MVS				78.65 64	83.44 104	66.85 115	83.62 51				86.12 191	66.82 137	86.01 35	61.72 192	89.79 159	83.08 203

LFMVS		67.06 283	67.89 264	64.56 334	78.02 189	38.25 456	70.81 241	59.60 418	65.18 96	71.06 344	86.56 175	43.85 370	75.22 255	46.35 373	89.63 160	80.21 286

TSAR-MVS + GP.		73.08 144	71.60 195	77.54 83	78.99 177	70.73 72	74.96 156	69.38 329	60.73 143	74.39 268	78.44 367	57.72 265	82.78 109	60.16 213	89.60 161	79.11 302

EC-MVSNet		77.08 85	77.39 87	76.14 103	76.86 219	56.87 236	80.32 84	87.52 12	63.45 118	74.66 259	84.52 220	69.87 102	84.94 68	69.76 104	89.59 162	86.60 76

MIMVSNet1		66.57 290	69.23 238	58.59 427	81.26 139	37.73 464	64.06 379	57.62 429	57.02 182	78.40 160	90.75 52	62.65 182	58.10 446	41.77 412	89.58 163	79.95 288

mmtdpeth		68.76 246	70.55 214	63.40 356	67.06 422	56.26 239	68.73 292	71.22 311	55.47 208	70.09 357	88.64 117	65.29 160	56.89 451	58.94 233	89.50 164	77.04 346

TransMVSNet (Re)		69.62 227	71.63 192	63.57 349	76.51 224	35.93 479	65.75 347	71.29 307	61.05 138	75.02 249	89.90 86	65.88 152	70.41 341	49.79 332	89.48 165	84.38 158

ACMMP++_ref															89.47 166

test2506		61.23 371	60.85 374	62.38 372	78.80 178	27.88 523	67.33 317	37.42 542	54.23 233	67.55 399	88.68 115	17.87 545	74.39 272	46.33 374	89.41 167	84.86 130

ECVR-MVS		64.82 315	65.22 310	63.60 348	78.80 178	31.14 508	66.97 327	56.47 444	54.23 233	69.94 361	88.68 115	37.23 427	74.81 265	45.28 386	89.41 167	84.86 130

SPE-MVS-test		74.89 113	74.23 126	76.86 91	77.01 209	62.94 164	78.98 100	84.61 63	58.62 160	70.17 356	80.80 315	66.74 141	81.96 126	61.74 191	89.40 169	85.69 106

PCF-MVS	63.80 13	72.70 161	71.69 189	75.72 107	78.10 186	60.01 199	73.04 191	81.50 131	45.34 383	79.66 139	84.35 224	65.15 161	82.65 111	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
SIFT-NCMNet		56.27 424	55.94 428	57.26 439	62.54 472	64.28 149	59.61 432	41.26 534	43.43 416	78.50 159	69.35 478	32.26 459	45.98 505	27.16 525	89.34 171	61.53 508

gbinet_0.2-2-1-0.02		62.58 352	61.83 357	64.86 332	67.07 419	41.37 417	61.56 405	67.91 354	49.27 321	66.62 408	67.23 501	41.53 395	74.46 270	45.94 378	89.31 172	78.74 308

HQP3-MVS								84.12 79							89.16 173

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	71.58 333	85.96 197	58.09 258	85.30 59	67.38 131	89.16 173	83.73 177

AUN-MVS		70.22 214	67.88 265	77.22 90	82.96 114	71.61 61	69.08 276	71.39 303	49.17 325	71.70 327	78.07 374	37.62 426	79.21 177	61.81 189	89.15 175	80.82 268

v10		75.69 96	76.20 97	74.16 129	74.44 266	48.69 312	75.84 149	82.93 100	59.02 157	85.92 50	89.17 100	58.56 251	82.74 110	70.73 94	89.14 176	91.05 13

MM		78.15 76	77.68 82	79.55 49	80.10 151	65.47 132	80.94 74	78.74 201	71.22 49	72.40 314	88.70 113	60.51 218	87.70 3	77.40 37	89.13 177	85.48 110

hse-mvs2		72.32 170	70.66 213	77.31 89	83.10 110	71.77 60	69.19 273	71.45 302	54.28 231	77.89 166	78.26 369	49.04 337	79.23 176	63.62 172	89.13 177	80.92 265

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 85	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 85	74.70 54	89.10 179	89.28 28

MCST-MVS		73.42 132	73.34 150	73.63 139	81.28 138	59.17 208	74.80 161	83.13 93	45.50 378	72.84 305	83.78 244	65.15 161	80.99 146	64.54 157	89.09 181	80.73 272

MGCNet		75.45 100	74.66 114	77.83 79	75.58 240	61.53 175	78.29 107	77.18 229	63.15 124	69.97 360	87.20 144	57.54 267	87.05 9	74.05 66	88.96 182	84.89 127

ITE_SJBPF				80.35 41	76.94 211	73.60 51		80.48 160	66.87 75	83.64 88	86.18 186	70.25 98	79.90 168	61.12 201	88.95 183	87.56 59

ArgMatch-SfM		64.74 318	63.70 334	67.83 286	77.62 198	76.78 30	67.30 319	58.21 427	36.64 480	81.94 108	73.41 426	38.67 418	56.92 450	50.66 326	88.89 184	69.81 435

ANet_high		67.08 281	69.94 220	58.51 428	57.55 513	27.09 526	58.43 449	76.80 234	63.56 115	82.40 102	91.93 25	59.82 230	64.98 407	50.10 331	88.86 185	83.46 186

test_0402		78.17 75	79.48 66	74.24 127	83.50 101	59.15 209	72.52 197	74.60 260	75.34 18	88.69 17	91.81 30	75.06 49	82.37 118	65.10 148	88.68 186	81.20 256

ArgMatch-Sym		63.94 331	63.05 346	66.61 312	76.68 221	75.81 34	65.98 341	57.57 430	35.60 488	80.60 130	69.62 473	43.62 374	55.74 453	49.14 343	88.61 187	68.29 451

APD_test1		75.04 108	75.38 107	74.02 132	69.89 367	70.15 77	76.46 132	79.71 177	65.50 88	82.99 93	88.60 118	66.94 134	72.35 304	59.77 222	88.54 188	79.56 293

mvs5depth		66.35 294	67.98 262	61.47 387	62.43 475	51.05 283	69.38 266	69.24 331	56.74 188	73.62 286	89.06 105	46.96 353	58.63 439	55.87 271	88.49 189	74.73 377

viewdifsd2359ckpt09		72.87 156	72.43 174	74.17 128	74.45 264	51.70 276	76.39 137	84.50 67	49.48 318	75.34 241	83.23 259	63.12 176	82.43 116	56.99 259	88.41 190	88.37 51

casdiffmvs_mvg		75.26 103	76.18 98	72.52 179	72.87 309	49.47 305	72.94 194	84.71 58	59.49 151	80.90 127	88.81 112	70.07 99	79.71 170	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
EGC-MVSNET		64.77 317	61.17 368	75.60 110	86.90 42	74.47 43	84.04 44	68.62 349	0.60 554	1.13 558	91.61 35	65.32 159	74.15 277	64.01 162	88.28 192	78.17 320

FE-MVSNET2		68.70 249	69.85 223	65.22 326	74.82 251	37.95 461	67.28 321	73.47 270	53.40 253	77.65 175	87.72 140	59.72 232	73.17 290	46.39 372	88.23 193	84.56 149

IterMVS-LS		73.01 148	73.12 155	72.66 175	73.79 284	49.90 298	71.63 225	78.44 207	58.22 165	80.51 131	86.63 172	58.15 256	79.62 171	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.
MSLP-MVS++		74.48 117	75.78 101	70.59 212	84.66 83	62.40 166	78.65 102	84.24 76	60.55 144	77.71 173	81.98 288	63.12 176	77.64 214	62.95 180	88.14 195	71.73 416

CL-MVSNet_self_test		62.44 354	63.40 340	59.55 416	72.34 318	32.38 500	56.39 462	64.84 379	51.21 288	67.46 400	81.01 311	50.75 322	63.51 414	38.47 440	88.12 196	82.75 216

casdiffseed414692147		74.13 119	74.76 113	72.25 188	73.89 282	49.89 302	75.54 151	82.35 115	58.57 163	77.77 170	87.76 139	69.09 109	78.46 192	59.77 222	88.10 197	88.41 48

FMVSNet1		71.06 195	72.48 172	66.81 306	77.65 197	40.68 428	71.96 211	73.03 274	61.14 137	79.45 143	90.36 73	60.44 220	75.20 257	50.20 330	88.05 198	84.54 150

pm-mvs1		68.40 254	69.85 223	64.04 341	73.10 300	39.94 438	64.61 370	70.50 319	55.52 207	73.97 280	89.33 93	63.91 173	68.38 367	49.68 335	88.02 199	83.81 173

TinyColmap		67.98 262	69.28 235	64.08 339	67.98 402	46.82 352	70.04 252	75.26 252	53.05 255	77.36 181	86.79 160	59.39 237	72.59 300	45.64 381	88.01 200	72.83 400

v8		75.07 107	75.64 103	73.35 145	73.42 290	47.46 339	75.20 153	81.45 133	60.05 147	85.64 54	89.26 95	58.08 260	81.80 131	69.71 106	87.97 201	90.79 17

BP-MVS1		71.60 184	70.06 218	76.20 102	74.07 276	55.22 250	74.29 173	73.44 271	57.29 179	73.87 285	84.65 215	32.57 454	83.49 94	72.43 83	87.94 202	89.89 23

tttt0517		69.46 230	67.79 267	74.46 121	75.34 241	52.72 272	75.05 155	63.27 394	54.69 219	78.87 150	84.37 223	26.63 501	81.15 140	63.95 165	87.93 203	89.51 25

SIFT-PointCN		56.55 421	55.82 429	58.75 423	62.59 471	63.48 158	59.22 433	45.58 504	42.97 424	74.44 267	69.65 472	25.00 513	47.28 500	35.25 477	87.73 204	65.49 479

new-patchmatchnet		52.89 453	55.76 431	44.26 511	59.94 496	6.31 559	37.36 538	50.76 477	41.10 440	64.28 432	79.82 337	44.77 363	48.43 493	36.24 468	87.61 205	78.03 323

tfpnnormal		66.48 291	67.93 263	62.16 375	73.40 291	36.65 470	63.45 386	64.99 377	55.97 201	72.82 306	87.80 138	57.06 274	69.10 360	48.31 355	87.54 206	80.72 273

Anonymous202405211		66.02 298	66.89 286	63.43 355	74.22 270	38.14 457	59.00 437	66.13 367	63.33 121	69.76 365	85.95 198	51.88 311	70.50 338	44.23 389	87.52 207	81.64 252

c3_l		69.82 224	69.89 221	69.61 246	66.24 432	43.48 398	68.12 304	79.61 182	51.43 280	77.72 172	80.18 330	54.61 294	78.15 206	63.62 172	87.50 208	87.20 65

v144192		72.99 150	73.06 157	72.77 171	74.58 263	47.48 338	71.90 215	80.44 162	51.57 278	81.46 118	84.11 231	58.04 262	82.12 123	67.98 120	87.47 209	88.70 45

Patchmtry		60.91 377	63.01 348	54.62 454	66.10 436	26.27 532	67.47 312	56.40 445	54.05 239	72.04 323	86.66 169	33.19 447	60.17 429	43.69 391	87.45 210	77.42 331

hybridcas		73.97 122	75.17 108	70.38 216	73.56 285	47.22 344	72.99 193	82.30 116	56.94 183	79.54 140	88.05 133	72.64 69	76.88 232	63.11 179	87.43 211	87.04 69

SIFT-PCN-Cal		56.03 426	55.47 433	57.69 435	63.19 468	62.93 165	58.63 444	43.46 518	42.37 429	75.62 229	69.51 476	25.32 511	44.67 518	33.77 492	87.41 212	65.45 481

v1921920		72.96 153	72.98 159	72.89 166	74.67 255	47.58 336	71.92 214	80.69 153	51.70 277	81.69 115	83.89 241	56.58 279	82.25 121	68.34 114	87.36 213	88.82 42

CSCG		74.12 120	74.39 121	73.33 146	79.35 162	61.66 174	77.45 119	81.98 123	62.47 130	79.06 148	80.19 329	61.83 197	78.79 185	59.83 221	87.35 214	79.54 296

MGCFI-Net		71.70 182	73.10 156	67.49 292	73.23 294	43.08 403	72.06 207	82.43 113	54.58 222	75.97 223	82.00 286	72.42 70	75.22 255	57.84 248	87.34 215	84.18 163

v1192		73.40 137	73.42 145	73.32 147	74.65 258	48.67 313	72.21 203	81.73 127	52.76 260	81.85 109	84.56 218	57.12 272	82.24 122	68.58 112	87.33 216	89.06 35

LCM-MVSNet-Re		69.10 240	71.57 196	61.70 382	70.37 357	34.30 491	61.45 407	79.62 180	56.81 186	89.59 8	88.16 131	68.44 116	72.94 292	42.30 404	87.33 216	77.85 327

sasdasda		72.29 172	73.38 147	69.04 258	74.23 268	47.37 340	73.93 178	83.18 90	54.36 229	76.61 207	81.64 299	72.03 72	75.34 252	57.12 255	87.28 218	84.40 156

canonicalmvs		72.29 172	73.38 147	69.04 258	74.23 268	47.37 340	73.93 178	83.18 90	54.36 229	76.61 207	81.64 299	72.03 72	75.34 252	57.12 255	87.28 218	84.40 156

baseline		73.10 143	73.96 133	70.51 214	71.46 332	46.39 364	72.08 206	84.40 69	55.95 202	76.62 206	86.46 179	67.20 131	78.03 207	64.22 161	87.27 220	87.11 68

SIFT-CM-Cal		57.90 406	56.75 416	61.34 390	65.62 440	67.48 106	60.91 414	44.69 508	44.05 404	73.16 298	71.09 454	30.69 480	50.23 477	33.27 496	87.25 221	66.31 472

wanda-best-256-512		61.16 373	60.55 377	62.98 361	66.67 426	39.85 440	58.66 442	68.87 340	46.67 362	64.46 427	67.75 493	41.94 389	71.84 318	42.67 400	87.24 222	77.26 336

FE-blended-shiyan7		61.16 373	60.55 377	62.98 361	66.67 426	39.85 440	58.66 442	68.87 340	46.67 362	64.46 427	67.75 493	41.94 389	71.84 318	42.67 400	87.24 222	77.26 336

blended_shiyan6		62.20 357	61.77 358	63.47 352	67.98 402	40.64 432	60.46 422	69.15 332	47.24 356	66.43 410	70.57 457	43.73 373	71.93 316	43.16 397	87.24 222	77.85 327

usedtu_blend_shiyan5		63.30 339	63.13 344	63.78 344	66.67 426	41.75 415	68.57 295	73.64 267	57.20 181	64.46 427	67.75 493	41.94 389	72.34 305	40.72 423	87.24 222	77.26 336

test_fmvsmconf0.01_n		73.91 123	73.64 139	74.71 118	69.79 371	66.25 123	75.90 147	79.90 173	46.03 372	76.48 214	85.02 210	67.96 126	73.97 279	74.47 60	87.22 226	83.90 171

alignmvs		70.54 207	71.00 205	69.15 256	73.50 287	48.04 326	69.85 257	79.62 180	53.94 243	76.54 211	82.00 286	59.00 243	74.68 266	57.32 253	87.21 227	84.72 140

LoFTR		61.29 370	62.50 353	57.67 437	69.07 382	65.66 131	68.96 278	48.59 490	43.15 421	86.65 39	79.95 334	32.68 453	53.14 464	46.21 375	87.20 228	54.22 523

blended_shiyan8		62.19 358	61.77 358	63.46 353	68.01 400	40.65 431	60.47 421	69.13 335	47.24 356	66.44 409	70.55 458	43.75 372	71.91 317	43.18 396	87.19 229	77.81 329

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	72.27 315	84.00 236	64.56 168	83.07 103	51.48 317	87.19 229	82.56 224

TSAR-MVS + MP.		79.05 64	78.81 69	79.74 45	88.94 27	67.52 105	86.61 22	81.38 136	51.71 276	77.15 188	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
v1240		73.06 146	73.14 153	72.84 169	74.74 254	47.27 343	71.88 216	81.11 143	51.80 275	82.28 103	84.21 225	56.22 283	82.34 119	68.82 111	87.17 231	88.91 40

SIFT-UM-Cal		57.67 408	56.99 413	59.70 412	64.92 453	66.46 120	59.84 430	46.03 502	44.18 403	76.77 202	71.89 445	29.03 494	48.71 487	33.08 498	87.13 233	63.93 494

GDP-MVS		70.84 201	69.24 237	75.62 109	76.44 225	55.65 246	74.62 168	82.78 104	49.63 313	72.10 320	83.79 243	31.86 465	82.84 108	64.93 151	87.01 234	88.39 50

test_fmvsmconf0.1_n		73.26 141	72.82 164	74.56 120	69.10 381	66.18 125	74.65 167	79.34 187	45.58 377	75.54 232	83.91 240	67.19 132	73.88 282	73.26 72	86.86 235	83.63 179

v1144		73.29 140	73.39 146	73.01 157	74.12 273	48.11 323	72.01 209	81.08 146	53.83 244	81.77 111	84.68 213	58.07 261	81.91 127	68.10 116	86.86 235	88.99 38

casdiffmvs		73.06 146	73.84 134	70.72 210	71.32 335	46.71 355	70.93 238	84.26 75	55.62 205	77.46 180	87.10 146	67.09 133	77.81 210	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
SIFT-ConvMatch		58.61 400	57.61 407	61.63 383	65.55 442	67.97 98	62.24 398	42.52 524	44.40 400	77.28 183	73.28 429	30.00 486	50.42 474	36.36 465	86.82 238	66.50 470

Vis-MVSNet (Re-imp)		62.74 349	63.21 343	61.34 390	72.19 321	31.56 505	67.31 318	53.87 457	53.60 250	69.88 362	83.37 251	40.52 404	70.98 333	41.40 414	86.78 239	81.48 254

CS-MVS		76.51 89	76.00 99	78.06 78	77.02 208	64.77 141	80.78 76	82.66 107	60.39 145	74.15 272	83.30 255	69.65 105	82.07 124	69.27 108	86.75 240	87.36 61

K. test v3		73.67 126	73.61 141	73.87 135	79.78 155	55.62 248	74.69 165	62.04 404	66.16 84	84.76 73	93.23 7	49.47 331	80.97 148	65.66 146	86.67 241	85.02 126

test_fmvsmconf_n		72.91 154	72.40 175	74.46 121	68.62 386	66.12 126	74.21 175	78.80 199	45.64 376	74.62 261	83.25 258	66.80 140	73.86 283	72.97 75	86.66 242	83.39 190

thisisatest0530		67.05 284	65.16 312	72.73 174	73.10 300	50.55 287	71.26 234	63.91 388	50.22 306	74.46 266	80.75 316	26.81 500	80.25 162	59.43 226	86.50 243	87.37 60

lessismore_v0				72.75 172	79.60 159	56.83 237		57.37 433		83.80 86	89.01 106	47.45 351	78.74 186	64.39 159	86.49 244	82.69 220

MVSMamba_PlusPlus		76.88 86	78.21 78	72.88 167	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 82	70.51 98	86.15 245	85.99 96

MVS_111021_HR		72.98 151	72.97 160	72.99 158	80.82 143	65.47 132	68.81 286	72.77 283	57.67 173	75.76 225	82.38 279	71.01 89	77.17 222	61.38 196	86.15 245	76.32 355

LF4IMVS		67.50 269	67.31 275	68.08 281	58.86 505	61.93 170	71.43 228	75.90 247	44.67 397	72.42 313	80.20 328	57.16 270	70.44 339	58.99 232	86.12 247	71.88 413

FMVSNet2		67.48 270	68.21 258	65.29 325	73.14 297	38.94 449	68.81 286	71.21 312	54.81 214	76.73 203	86.48 178	48.63 343	74.60 267	47.98 359	86.11 248	82.35 229

MatchFormer		53.09 450	55.03 440	47.30 495	59.31 501	57.25 233	67.30 319	37.25 544	27.23 526	82.61 100	74.56 408	26.23 505	42.89 525	34.73 483	86.00 249	41.75 541

EPNet_dtu		58.93 396	58.52 395	60.16 410	67.91 404	47.70 334	69.97 254	58.02 428	49.73 312	47.28 532	73.02 431	38.14 420	62.34 418	36.57 464	85.99 250	70.43 430
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SIFT-UMatch		58.13 403	57.37 411	60.42 405	65.49 444	67.10 112	61.52 406	43.57 516	44.20 402	76.80 200	72.60 433	29.70 489	47.95 496	36.61 462	85.82 251	66.20 474

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	78.33 200	74.73 52	85.79 252	82.35 229

BridgeMVS		73.59 129	74.06 130	72.17 190	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 91	63.98 164	85.78 253	85.22 115

API-MVS		70.97 199	71.51 197	69.37 249	75.20 243	55.94 241	80.99 73	76.84 233	62.48 129	71.24 342	77.51 379	61.51 203	80.96 151	52.04 312	85.76 254	71.22 422

LuminaMVS		71.15 194	70.79 210	72.24 189	77.20 202	58.34 224	72.18 204	76.20 241	54.91 213	77.74 171	81.93 291	49.17 336	76.31 240	62.12 188	85.66 255	82.07 237

fmvsm_s_conf0.5_n_9		74.56 116	74.30 124	75.34 113	77.17 203	64.87 140	72.62 196	76.17 242	54.54 225	78.32 161	86.14 189	65.14 163	75.72 248	73.10 73	85.55 256	85.42 111

v2v482		72.55 166	72.58 169	72.43 181	72.92 308	46.72 354	71.41 229	79.13 192	55.27 209	81.17 122	85.25 208	55.41 289	81.13 141	67.25 135	85.46 257	89.43 26

GBi-Net		68.30 256	68.79 244	66.81 306	73.14 297	40.68 428	71.96 211	73.03 274	54.81 214	74.72 256	90.36 73	48.63 343	75.20 257	47.12 364	85.37 258	84.54 150

test1		68.30 256	68.79 244	66.81 306	73.14 297	40.68 428	71.96 211	73.03 274	54.81 214	74.72 256	90.36 73	48.63 343	75.20 257	47.12 364	85.37 258	84.54 150

FMVSNet3		65.00 312	65.16 312	64.52 335	69.47 375	37.56 466	66.63 332	70.38 320	51.55 279	74.72 256	83.27 256	37.89 424	74.44 271	47.12 364	85.37 258	81.57 253

CNLPA		73.44 131	73.03 158	74.66 119	78.27 183	75.29 37	75.99 146	78.49 206	65.39 91	75.67 228	83.22 263	61.23 207	66.77 392	53.70 304	85.33 261	81.92 244

Effi-MVS+-dtu		75.43 101	72.28 178	84.91 2	77.05 206	83.58 1	78.47 105	77.70 219	57.68 172	74.89 253	78.13 373	64.80 165	84.26 81	56.46 265	85.32 262	86.88 71

UGNet		70.20 215	69.05 240	73.65 137	76.24 228	63.64 155	75.87 148	72.53 287	61.48 135	60.93 468	86.14 189	52.37 309	77.12 227	50.67 325	85.21 263	80.17 287
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
VNet		64.01 330	65.15 314	60.57 400	73.28 293	35.61 482	57.60 454	67.08 359	54.61 221	66.76 406	83.37 251	56.28 282	66.87 388	42.19 406	85.20 264	79.23 301

TAMVS		65.31 306	63.75 332	69.97 239	82.23 125	59.76 202	66.78 331	63.37 393	45.20 389	69.79 364	79.37 350	47.42 352	72.17 308	34.48 485	85.15 265	77.99 325

test_yl		65.11 308	65.09 317	65.18 327	70.59 347	40.86 423	63.22 391	72.79 281	57.91 169	68.88 381	79.07 361	42.85 384	74.89 263	45.50 383	84.97 266	79.81 289

DCV-MVSNet		65.11 308	65.09 317	65.18 327	70.59 347	40.86 423	63.22 391	72.79 281	57.91 169	68.88 381	79.07 361	42.85 384	74.89 263	45.50 383	84.97 266	79.81 289

USDC		62.80 346	63.10 345	61.89 378	65.19 447	43.30 401	67.42 313	74.20 265	35.80 487	72.25 316	84.48 221	45.67 357	71.95 315	37.95 447	84.97 266	70.42 431

ETV-MVS		72.72 160	72.16 181	74.38 126	76.90 217	55.95 240	73.34 186	84.67 59	62.04 131	72.19 318	70.81 455	65.90 151	85.24 63	58.64 237	84.96 269	81.95 243

DPM-MVS		69.98 220	69.22 239	72.26 186	82.69 118	58.82 216	70.53 244	81.23 140	47.79 348	64.16 436	80.21 327	51.32 317	83.12 101	60.14 215	84.95 270	74.83 374

viewdifsd2359ckpt11		69.22 235	69.68 227	67.83 286	68.17 397	46.57 358	66.42 336	68.93 338	50.60 299	77.47 179	83.95 237	68.16 119	73.84 284	58.49 239	84.92 271	83.10 200

viewmsd2359difaftdt		69.22 235	69.68 227	67.83 286	68.17 397	46.57 358	66.42 336	68.93 338	50.60 299	77.48 178	83.94 238	68.16 119	73.84 284	58.49 239	84.92 271	83.10 200

mamba_0408		70.32 211	69.35 231	73.24 148	76.92 212	55.22 250	56.61 460	79.27 189	52.14 269	73.08 300	83.14 265	60.53 216	82.50 113	57.51 250	84.91 273	81.99 240

SSM_04072		67.23 278	69.35 231	60.89 397	76.92 212	55.22 250	56.61 460	79.27 189	52.14 269	73.08 300	83.14 265	60.53 216	45.46 510	57.51 250	84.91 273	81.99 240

SSM_0407		72.15 174	71.85 186	73.06 156	76.92 212	55.22 250	73.59 180	79.83 174	53.69 246	73.08 300	84.18 226	62.26 191	81.98 125	58.21 243	84.91 273	81.99 240

SIFT-NN-CMatch		57.48 411	56.23 421	61.21 393	63.66 465	67.89 100	60.78 417	40.90 537	41.97 432	71.65 329	71.96 443	32.11 460	49.35 482	38.19 444	84.88 276	66.37 471

viewmacassd2359aftdt		71.41 189	72.29 177	68.78 269	71.32 335	44.81 380	70.11 251	81.51 130	52.64 262	74.95 251	86.79 160	66.02 148	74.50 269	62.43 185	84.86 277	87.03 70

SIFT-NCM-Cal		58.68 398	57.65 405	61.77 381	67.58 411	68.99 94	62.62 394	43.04 521	44.65 398	75.91 224	72.23 437	33.66 444	49.28 484	34.36 486	84.76 278	67.03 463

TestfortrainingZip				73.58 141	79.21 166	57.65 230	86.10 28	81.22 141	72.34 42	72.08 322	83.19 264	58.95 244	83.71 88		84.76 278	79.38 299

SDMVSNet		66.36 293	67.85 266	61.88 379	73.04 303	46.14 367	58.54 447	71.36 304	51.42 281	68.93 377	82.72 271	65.62 154	62.22 420	54.41 294	84.67 280	77.28 333

sd_testset		63.55 333	65.38 308	58.07 431	73.04 303	38.83 451	57.41 455	65.44 374	51.42 281	68.93 377	82.72 271	63.76 174	58.11 445	41.05 417	84.67 280	77.28 333

eth_miper_zixun_eth		69.42 231	68.73 248	71.50 199	67.99 401	46.42 362	67.58 309	78.81 197	50.72 296	78.13 164	80.34 325	50.15 326	80.34 160	60.18 212	84.65 282	87.74 56

miper_lstm_enhance		61.97 360	61.63 363	62.98 361	60.04 492	45.74 370	47.53 511	70.95 314	44.04 405	73.06 303	78.84 364	39.72 410	60.33 428	55.82 273	84.64 283	82.88 210

SSM_0404		72.51 167	72.15 182	73.60 140	78.20 184	55.86 243	74.41 170	79.83 174	53.69 246	73.98 279	84.18 226	62.26 191	82.50 113	58.21 243	84.60 284	82.43 227

cl22		67.14 279	66.51 290	69.03 260	63.20 467	43.46 399	66.88 330	76.25 240	49.22 324	74.48 265	77.88 375	45.49 359	77.40 217	60.64 207	84.59 285	86.24 87

miper_ehance_all_eth		68.36 255	68.16 261	68.98 262	65.14 450	43.34 400	67.07 325	78.92 196	49.11 326	76.21 220	77.72 376	53.48 301	77.92 209	61.16 200	84.59 285	85.68 107

miper_enhance_ethall		65.86 300	65.05 320	68.28 280	61.62 481	42.62 408	64.74 366	77.97 216	42.52 427	73.42 293	72.79 432	49.66 329	77.68 213	58.12 245	84.59 285	84.54 150

XFeat-MNN		48.68 483	49.35 481	46.65 500	44.49 548	46.89 351	46.91 514	43.80 515	27.16 527	75.21 244	60.05 526	22.65 526	46.52 502	39.33 430	84.57 288	46.53 534

balanced_ft_v1		71.65 183	72.22 180	69.92 240	74.26 267	45.74 370	81.54 70	79.66 178	53.65 248	79.77 138	86.74 164	51.20 319	80.64 154	58.70 236	84.47 289	83.40 189

SIFT-NN-PointCN		57.17 416	56.12 424	60.35 408	62.47 474	65.79 129	59.98 427	44.36 512	42.73 425	72.13 319	71.16 453	30.84 477	48.08 495	36.92 459	84.45 290	67.17 462

KinetiMVS		72.61 163	72.54 170	72.82 170	71.47 331	55.27 249	68.54 296	76.50 236	61.70 134	74.95 251	86.08 193	59.17 241	76.95 229	69.96 101	84.45 290	86.24 87

CDS-MVSNet		64.33 326	62.66 352	69.35 251	80.44 147	58.28 225	65.26 355	65.66 371	44.36 401	67.30 402	75.54 398	43.27 376	71.77 320	37.68 449	84.44 292	78.01 324
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
testing3-2		56.85 418	57.62 406	54.53 455	75.84 236	22.23 544	51.26 498	49.10 487	61.04 139	63.74 444	79.73 339	22.29 527	59.44 432	31.16 507	84.43 293	81.92 244

E5new		73.42 132	74.46 117	70.29 222	74.61 259	47.14 345	71.85 219	83.01 94	56.07 196	77.28 183	86.81 155	71.54 79	77.15 223	64.59 153	84.39 294	86.59 77

E6new		73.42 132	74.46 117	70.29 222	74.60 261	47.14 345	71.86 217	82.99 96	56.07 196	77.28 183	86.81 155	71.55 77	77.14 225	64.59 153	84.39 294	86.59 77

E6		73.42 132	74.46 117	70.29 222	74.60 261	47.14 345	71.86 217	82.99 96	56.07 196	77.28 183	86.81 155	71.55 77	77.14 225	64.59 153	84.39 294	86.59 77

E5		73.42 132	74.46 117	70.29 222	74.61 259	47.14 345	71.85 219	83.01 94	56.07 196	77.28 183	86.81 155	71.54 79	77.15 223	64.59 153	84.39 294	86.59 77

CANet		73.00 149	71.84 187	76.48 97	75.82 237	61.28 179	74.81 159	80.37 164	63.17 122	62.43 456	80.50 322	61.10 211	85.16 67	64.00 163	84.34 298	83.01 206

PLC	62.01 16	71.79 181	70.28 217	76.33 99	80.31 149	68.63 95	78.18 111	81.24 139	54.57 223	67.09 404	80.63 319	59.44 236	81.74 133	46.91 367	84.17 299	78.63 309
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PVSNet_BlendedMVS		65.38 305	64.30 325	68.61 272	69.81 368	49.36 306	65.60 350	78.96 194	45.50 378	59.98 472	78.61 365	51.82 312	78.20 203	44.30 387	84.11 300	78.27 317

cascas		64.59 320	62.77 351	70.05 236	75.27 242	50.02 295	61.79 401	71.61 297	42.46 428	63.68 445	68.89 485	49.33 333	80.35 159	47.82 361	84.05 301	79.78 291

SIFT-NN-UMatch		57.27 415	56.18 422	60.54 402	62.85 470	66.67 118	61.19 411	41.27 533	43.01 423	70.01 359	72.44 436	32.76 451	49.32 483	38.19 444	83.87 302	65.63 478

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
test20.03		55.74 429	57.51 409	50.42 477	59.89 497	32.09 502	50.63 499	49.01 488	50.11 307	65.07 421	83.23 259	45.61 358	48.11 494	30.22 510	83.82 304	71.07 426

fmvsm_s_conf0.5_n_6		70.08 217	69.97 219	70.39 215	72.99 306	58.93 215	68.84 282	76.40 239	49.08 327	68.75 385	81.65 298	57.34 269	71.97 314	70.91 92	83.81 305	80.26 284

SIFT-MNN		59.60 389	58.57 394	62.71 368	68.39 389	69.16 90	63.67 384	48.13 493	45.22 388	73.92 282	73.85 420	30.71 479	50.57 473	39.45 428	83.78 306	68.40 449

D2MVS		62.58 352	61.05 370	67.20 298	63.85 461	47.92 327	56.29 463	69.58 326	39.32 456	70.07 358	78.19 371	34.93 438	72.68 294	53.44 307	83.74 307	81.00 263

MVS_111021_LR		72.10 175	71.82 188	72.95 160	79.53 160	73.90 49	70.45 246	66.64 362	56.87 184	76.81 199	81.76 295	68.78 110	71.76 321	61.81 189	83.74 307	73.18 394

PDCNetPlus		38.77 507	39.67 512	36.07 526	38.82 554	27.82 524	36.52 540	51.55 474	22.53 542	37.81 548	50.69 538	7.16 557	32.98 543	28.21 522	83.73 309	47.40 531

patch_mono-2		62.73 350	64.08 329	58.68 426	70.36 358	55.87 242	60.84 416	64.11 387	41.23 439	64.04 437	78.22 370	60.00 225	48.80 486	54.17 299	83.71 310	71.37 419

dcpmvs_2		71.02 198	72.65 166	66.16 317	76.06 234	50.49 288	71.97 210	79.36 186	50.34 303	82.81 97	83.63 245	64.38 169	67.27 381	61.54 193	83.71 310	80.71 274

fmvsm_s_conf0.5_n_10		72.30 171	72.02 183	73.15 152	70.76 343	59.05 212	73.40 185	79.63 179	48.80 333	75.39 240	84.03 233	59.60 235	75.18 260	72.85 76	83.68 312	85.21 118

test_fmvsmvis_n_1920		72.36 169	72.49 171	71.96 191	71.29 337	64.06 153	72.79 195	81.82 125	40.23 451	81.25 121	81.04 310	70.62 93	68.69 362	69.74 105	83.60 313	83.14 199

thres600view7		61.82 363	61.38 366	63.12 359	71.81 326	34.93 486	64.64 368	56.99 438	54.78 218	70.33 352	79.74 338	32.07 462	72.42 303	38.61 438	83.46 314	82.02 238

viewmanbaseed2359cas		70.24 212	70.83 208	68.48 274	69.99 366	44.55 386	69.48 263	81.01 148	50.87 293	73.61 287	84.84 212	64.00 171	74.31 274	60.24 210	83.43 315	86.56 81

旧先验1					84.55 86	60.36 194		63.69 389			87.05 150	54.65 293			83.34 316	69.66 438

SSC-MVS3.2		57.01 417	59.50 387	49.57 484	67.73 407	25.95 534	46.68 515	51.75 472	51.41 283	63.84 441	79.66 341	53.28 303	50.34 476	37.85 448	83.28 317	72.41 406

新几何1				69.99 237	88.37 34	71.34 64		62.08 401	43.85 406	74.99 250	86.11 192	52.85 305	70.57 337	50.99 323	83.23 318	68.05 457

fmvsm_l_conf0.5_n_9		70.73 204	71.08 203	69.67 245	70.44 355	58.80 217	70.21 250	75.11 255	48.15 342	73.50 290	82.69 273	65.69 153	68.05 373	70.87 93	83.02 319	82.16 234

Vis-MVSNet		74.85 115	74.56 115	75.72 107	81.63 133	64.64 142	76.35 138	79.06 193	62.85 126	73.33 294	88.41 121	62.54 186	79.59 173	63.94 167	82.92 320	82.94 207
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
fmvsm_s_conf0.5_n_8		72.87 156	72.85 161	72.93 163	72.25 319	59.01 214	72.35 200	80.13 169	56.32 193	75.74 226	84.12 229	60.14 224	75.05 261	71.71 87	82.90 321	84.75 137

guyue		66.95 286	66.74 289	67.56 291	70.12 365	51.14 282	65.05 360	68.68 347	49.98 311	74.64 260	80.83 314	50.77 321	70.34 342	57.72 249	82.89 322	81.21 255

ET-MVSNet_ETH3D		63.32 338	60.69 376	71.20 205	70.15 363	55.66 245	65.02 361	64.32 385	43.28 420	68.99 373	72.05 442	25.46 509	78.19 205	54.16 300	82.80 323	79.74 292

E4		72.74 159	73.54 142	70.35 219	74.85 250	46.82 352	69.53 261	82.80 101	55.60 206	76.23 219	86.50 177	69.87 102	77.45 216	63.72 169	82.77 324	86.76 74

DELS-MVS		68.83 244	68.31 253	70.38 216	70.55 351	48.31 319	63.78 383	82.13 120	54.00 240	68.96 374	75.17 403	58.95 244	80.06 167	58.55 238	82.74 325	82.76 215
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
CMPMVS	48.73 20	61.54 369	60.89 373	63.52 350	61.08 483	51.55 278	68.07 305	68.00 353	33.88 497	65.87 414	81.25 305	37.91 423	67.71 374	49.32 340	82.60 326	71.31 421
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
VortexMVS		65.93 299	66.04 300	65.58 324	67.63 410	47.55 337	64.81 363	72.75 284	47.37 353	75.17 247	79.62 343	49.28 334	71.00 332	55.20 279	82.51 327	78.21 319

ppachtmachnet_test		60.26 384	59.61 385	62.20 373	67.70 408	44.33 389	58.18 451	60.96 408	40.75 447	65.80 415	72.57 435	41.23 397	63.92 411	46.87 368	82.42 328	78.33 315

SP-MNN		63.33 337	64.30 325	60.41 406	66.01 437	60.04 198	65.58 351	60.61 409	49.33 319	69.45 367	73.75 421	41.65 393	48.61 489	69.96 101	82.36 329	72.57 403

AstraMVS		67.11 280	66.84 288	67.92 282	70.75 344	51.36 280	64.77 365	67.06 360	49.03 329	75.40 237	82.05 284	51.26 318	70.65 335	58.89 234	82.32 330	81.77 249

v148		69.38 233	69.39 230	69.36 250	69.14 380	44.56 384	68.83 284	72.70 285	54.79 217	78.59 155	84.12 229	54.69 292	76.74 236	59.40 227	82.20 331	86.79 72

thisisatest0515		60.48 382	57.86 403	68.34 277	67.25 414	46.42 362	60.58 420	62.14 399	40.82 445	63.58 448	69.12 479	26.28 504	78.34 199	48.83 346	82.13 332	80.26 284

fmvsm_s_conf0.5_n_5		71.46 188	71.62 193	70.99 207	73.89 282	59.95 200	73.02 192	73.08 273	45.15 390	77.30 182	84.06 232	64.73 167	70.08 346	71.20 88	82.10 333	82.92 208

OpenMVS	62.51 15	68.76 246	68.75 246	68.78 269	70.56 349	53.91 263	78.29 107	77.35 224	48.85 332	70.22 353	83.52 247	52.65 308	76.93 230	55.31 278	81.99 334	75.49 365

MAR-MVS		67.72 267	66.16 295	72.40 182	74.45 264	64.99 139	74.87 157	77.50 222	48.67 335	65.78 416	68.58 489	57.01 275	77.79 211	46.68 370	81.92 335	74.42 384
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
Anonymous20231206		54.13 440	55.82 429	49.04 489	70.89 338	35.96 478	51.73 494	50.87 476	34.86 490	62.49 455	79.22 356	42.52 387	44.29 520	27.95 523	81.88 336	66.88 465

SIFT-NN-NCMNet		57.48 411	56.02 426	61.86 380	66.93 424	69.26 89	62.14 399	44.46 511	42.32 430	67.01 405	71.93 444	32.46 456	50.96 471	35.06 480	81.87 337	65.36 482

FE-MVS		68.29 258	66.96 283	72.26 186	74.16 272	54.24 260	77.55 117	73.42 272	57.65 175	72.66 309	84.91 211	32.02 464	81.49 135	48.43 353	81.85 338	81.04 260

GeoE		73.14 142	73.77 137	71.26 203	78.09 187	52.64 273	74.32 171	79.56 184	56.32 193	76.35 218	83.36 253	70.76 92	77.96 208	63.32 176	81.84 339	83.18 198

FA-MVS(test-final)		71.27 192	71.06 204	71.92 193	73.96 279	52.32 275	76.45 133	76.12 243	59.07 156	74.04 278	86.18 186	52.18 310	79.43 175	59.75 224	81.76 340	84.03 167

E3		71.98 177	72.60 167	70.13 232	74.09 274	46.61 356	69.15 274	82.56 110	54.40 226	75.31 243	85.35 203	68.51 113	77.34 218	62.30 186	81.75 341	86.44 84

E2		71.98 177	72.60 167	70.13 232	74.09 274	46.61 356	69.15 274	82.56 110	54.40 226	75.32 242	85.35 203	68.51 113	77.34 218	62.30 186	81.74 342	86.44 84

thres100view900		61.17 372	61.09 369	61.39 388	72.14 322	35.01 485	65.42 353	56.99 438	55.23 210	70.71 347	79.90 336	32.07 462	72.09 310	35.61 474	81.73 343	77.08 343

tfpn200view9		60.35 383	59.97 382	61.51 385	70.78 341	35.35 483	63.27 389	57.47 431	53.00 257	68.31 391	77.09 383	32.45 457	72.09 310	35.61 474	81.73 343	77.08 343

thres400		60.77 380	59.97 382	63.15 358	70.78 341	35.35 483	63.27 389	57.47 431	53.00 257	68.31 391	77.09 383	32.45 457	72.09 310	35.61 474	81.73 343	82.02 238

MG-MVS		70.47 209	71.34 199	67.85 284	79.26 164	40.42 435	74.67 166	75.15 254	58.41 164	68.74 386	88.14 132	56.08 284	83.69 89	59.90 219	81.71 346	79.43 298

usedtu_dtu_shiyan1		61.16 373	60.92 371	61.90 376	69.70 373	36.41 474	58.57 445	68.86 342	44.94 394	65.02 422	75.67 394	43.00 381	70.28 343	40.83 420	81.68 347	78.99 304

FE-MVSNET3		61.16 373	60.92 371	61.90 376	69.70 373	36.41 474	58.57 445	68.86 342	44.94 394	65.02 422	75.67 394	43.00 381	70.28 343	40.82 421	81.68 347	78.99 304

PAPM_NR		73.91 123	74.16 128	73.16 150	81.90 129	53.50 266	81.28 72	81.40 134	66.17 83	73.30 295	83.31 254	59.96 226	83.10 102	58.45 241	81.66 349	82.87 211

FMVSNet5		55.08 436	55.54 432	53.71 457	65.80 438	33.50 496	56.22 464	52.50 467	43.72 412	61.06 465	83.38 250	25.46 509	54.87 457	30.11 511	81.64 350	72.75 401

viewdifsd2359ckpt07		70.24 212	71.30 200	67.05 302	70.55 351	43.90 393	67.15 323	77.48 223	53.60 250	75.49 234	85.35 203	71.42 84	72.13 309	59.03 231	81.60 351	85.12 120

SP-LightGlue		66.16 297	66.97 282	63.75 345	68.62 386	66.76 116	68.82 285	62.15 398	57.30 178	70.52 349	75.63 396	43.02 380	48.82 485	75.09 49	81.55 352	75.66 362

FE-MVSNET		62.77 347	64.36 324	57.97 434	70.52 353	33.96 492	61.66 404	67.88 355	50.67 297	73.18 297	82.58 275	48.03 348	68.22 369	43.21 395	81.55 352	71.74 415

fmvsm_s_conf0.5_n_3		72.97 152	74.13 129	69.47 248	71.40 333	58.36 223	73.07 189	80.64 156	56.86 185	75.49 234	84.67 214	67.86 127	72.33 307	75.68 45	81.54 354	77.73 330

diffmvs_AUTHOR		68.27 259	68.59 250	67.32 296	63.76 463	45.37 373	65.31 354	77.19 228	49.25 322	72.68 308	82.19 282	59.62 234	71.17 329	65.75 145	81.53 355	85.42 111

PAPR		69.20 237	68.66 249	70.82 208	75.15 245	47.77 331	75.31 152	81.11 143	49.62 315	66.33 411	79.27 355	61.53 202	82.96 104	48.12 357	81.50 356	81.74 251

SP-SuperGlue		66.58 289	67.36 272	64.24 336	68.59 388	66.47 119	68.14 302	61.29 407	58.07 167	71.67 328	75.95 391	46.37 354	50.95 472	74.72 53	81.46 357	75.29 371

testdata				64.13 338	85.87 64	63.34 160		61.80 405	47.83 347	76.42 217	86.60 174	48.83 340	62.31 419	54.46 293	81.26 358	66.74 468

onestephybrid01		68.67 251	68.21 258	70.07 235	64.40 458	49.83 304	67.51 310	76.41 238	51.08 290	71.78 325	81.97 290	59.69 233	75.32 254	59.85 220	81.20 359	85.06 125

icg_test_0407_2		63.88 332	65.59 304	58.75 423	72.47 313	48.64 314	53.19 484	72.98 277	45.33 384	68.91 379	79.37 350	61.91 195	51.11 469	55.06 281	81.11 360	76.49 349

IMVS_0407		67.26 276	67.35 273	66.97 305	72.47 313	48.64 314	69.03 277	72.98 277	45.33 384	68.91 379	79.37 350	61.91 195	75.77 245	55.06 281	81.11 360	76.49 349

IMVS_0404		62.18 359	63.05 346	59.58 415	72.47 313	48.64 314	55.47 470	72.98 277	45.33 384	55.80 500	79.37 350	49.84 328	53.60 462	55.06 281	81.11 360	76.49 349

IMVS_0403		67.07 282	67.08 278	67.03 303	72.47 313	48.64 314	68.44 300	72.98 277	45.33 384	68.63 387	79.37 350	60.38 221	75.97 241	55.06 281	81.11 360	76.49 349

3Dnovator	65.95 11	71.50 186	71.22 202	72.34 183	73.16 296	63.09 162	78.37 106	78.32 209	57.67 173	72.22 317	84.61 217	54.77 291	78.47 191	60.82 204	81.07 364	75.45 366

viewdifsd2359ckpt13		69.89 222	69.74 226	70.32 221	70.82 340	48.73 310	72.39 199	81.39 135	48.20 340	72.73 307	82.73 270	62.61 183	76.50 237	55.87 271	80.93 365	85.73 105

viewcassd2359sk11		71.41 189	71.89 184	69.98 238	73.50 287	46.46 361	68.91 281	82.39 114	53.62 249	74.57 263	84.41 222	67.40 130	77.27 220	61.35 197	80.89 366	86.21 90

testing3		58.28 402	58.38 398	58.00 433	77.45 201	26.12 533	60.78 417	43.00 522	56.02 200	70.18 355	75.76 392	13.27 553	67.24 382	48.02 358	80.89 366	80.65 275

RPSCF		75.76 95	74.37 122	79.93 43	74.81 252	77.53 21	77.53 118	79.30 188	59.44 152	78.88 149	89.80 87	71.26 86	73.09 291	57.45 252	80.89 366	89.17 33

EG-PatchMatch MVS		70.70 205	70.88 207	70.16 230	82.64 119	58.80 217	71.48 227	73.64 267	54.98 212	76.55 210	81.77 294	61.10 211	78.94 182	54.87 287	80.84 369	72.74 402

V42		71.06 195	70.83 208	71.72 194	67.25 414	47.14 345	65.94 342	80.35 165	51.35 284	83.40 90	83.23 259	59.25 239	78.80 184	65.91 143	80.81 370	89.23 31

fmvsm_s_conf0.5_n_7		67.30 275	66.92 284	68.43 275	72.78 311	58.22 226	60.90 415	72.51 289	49.62 315	63.66 446	80.65 318	58.56 251	68.63 364	62.83 181	80.76 371	78.45 313

ttmdpeth		56.40 423	55.45 434	59.25 417	55.63 523	40.69 427	58.94 439	49.72 481	36.22 482	65.39 417	86.97 151	23.16 522	56.69 452	42.30 404	80.74 372	80.36 282

fmvsm_s_conf0.1_n_2		69.14 239	68.42 252	71.28 202	68.30 394	57.60 231	65.06 359	69.91 323	48.24 338	74.56 264	82.84 268	55.55 288	69.73 350	70.66 96	80.69 373	86.52 82

test222					87.30 37	69.15 92	67.85 306	59.59 419	41.06 441	73.05 304	85.72 201	48.03 348			80.65 374	66.92 464

BH-untuned		69.39 232	69.46 229	69.18 255	77.96 191	56.88 235	68.47 299	77.53 221	56.77 187	77.79 169	79.63 342	60.30 223	80.20 165	46.04 377	80.65 374	70.47 429

pmmvs-eth3d		64.41 325	63.27 342	67.82 289	75.81 238	60.18 197	69.49 262	62.05 403	38.81 462	74.13 273	82.23 281	43.76 371	68.65 363	42.53 402	80.63 376	74.63 378

fmvsm_s_conf0.5_n_2		68.93 242	68.23 257	71.02 206	67.78 406	57.58 232	64.74 366	69.56 327	48.16 341	74.38 269	82.32 280	56.00 285	69.68 353	70.65 97	80.52 377	85.80 103

fmvsm_s_conf0.5_n_11		71.06 195	70.91 206	71.51 198	72.09 323	59.40 203	73.49 182	79.97 172	50.98 291	68.33 390	81.50 302	61.82 198	72.64 296	69.54 107	80.43 378	82.51 225

fmvsm_l_conf0.5_n_3		71.98 177	71.68 190	72.88 167	72.84 310	64.15 151	73.48 183	77.11 230	48.97 331	71.31 341	84.18 226	67.98 125	71.60 325	68.86 110	80.43 378	82.89 209

EI-MVSNet-Vis-set		72.78 158	71.87 185	75.54 111	74.77 253	59.02 213	72.24 202	71.56 299	63.92 110	78.59 155	71.59 447	66.22 147	78.60 188	67.58 124	80.32 380	89.00 37

diffmvs		67.42 273	67.50 270	67.20 298	62.26 477	45.21 376	64.87 362	77.04 231	48.21 339	71.74 326	79.70 340	58.40 253	71.17 329	64.99 149	80.27 381	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
SIFT-NN		56.62 420	55.34 437	60.47 403	67.01 423	67.25 109	61.74 402	45.38 507	42.69 426	64.49 426	71.36 452	28.48 495	47.55 497	36.68 461	80.23 382	66.63 469

MVStest1		55.38 433	54.97 441	56.58 444	43.72 549	40.07 437	59.13 435	47.09 498	34.83 491	76.53 212	84.65 215	13.55 552	53.30 463	55.04 285	80.23 382	76.38 354

EI-MVSNet-UG-set		72.63 162	71.68 190	75.47 112	74.67 255	58.64 221	72.02 208	71.50 300	63.53 116	78.58 157	71.39 451	65.98 149	78.53 189	67.30 134	80.18 384	89.23 31

E3new		70.94 200	71.30 200	69.86 242	72.98 307	46.34 365	68.74 291	82.28 117	53.01 256	73.95 281	83.57 246	66.41 145	77.21 221	60.68 206	80.06 385	86.03 95

MDA-MVSNet-bldmvs		62.34 355	61.73 360	64.16 337	61.64 480	49.90 298	48.11 509	57.24 436	53.31 254	80.95 124	79.39 349	49.00 339	61.55 423	45.92 379	80.05 386	81.03 261

reproduce_monomvs		58.94 395	58.14 400	61.35 389	59.70 499	40.98 422	60.24 425	63.51 391	45.85 375	68.95 375	75.31 402	18.27 543	65.82 400	51.47 318	79.97 387	77.26 336

IB-MVS	49.67 18	59.69 388	56.96 414	67.90 283	68.19 396	50.30 291	61.42 408	65.18 376	47.57 350	55.83 498	67.15 502	23.77 519	79.60 172	43.56 393	79.97 387	73.79 390
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
WBMVS		53.38 446	54.14 447	51.11 474	70.16 362	26.66 528	50.52 501	51.64 473	39.32 456	63.08 452	77.16 382	23.53 520	55.56 454	31.99 502	79.88 389	71.11 425

Patchmatch-RL test		59.95 386	59.12 389	62.44 371	72.46 317	54.61 258	59.63 431	47.51 496	41.05 442	74.58 262	74.30 413	31.06 474	65.31 404	51.61 316	79.85 390	67.39 459

EI-MVSNet		69.61 228	69.01 242	71.41 200	73.94 280	49.90 298	71.31 232	71.32 305	58.22 165	75.40 237	70.44 459	58.16 255	75.85 242	62.51 182	79.81 391	88.48 46

MVSTER		63.29 340	61.60 364	68.36 276	59.77 498	46.21 366	60.62 419	71.32 305	41.83 434	75.40 237	79.12 359	30.25 483	75.85 242	56.30 266	79.81 391	83.03 205

viewmamba		69.26 234	69.34 233	69.03 260	64.17 460	47.67 335	67.23 322	76.95 232	52.82 259	73.15 299	83.23 259	62.99 179	74.06 278	63.71 170	79.80 393	85.36 113

ab-mvs		64.11 328	65.13 315	61.05 394	71.99 324	38.03 460	67.59 308	68.79 346	49.08 327	65.32 419	86.26 184	58.02 263	66.85 390	39.33 430	79.79 394	78.27 317

dtuonlycased		61.79 364	62.24 356	60.43 404	73.00 305	39.07 446	61.74 402	60.61 409	33.09 503	74.10 274	80.34 325	59.20 240	60.39 427	38.34 441	79.76 395	81.83 246

PVSNet_Blended_VisFu		70.04 218	68.88 243	73.53 144	82.71 117	63.62 156	74.81 159	81.95 124	48.53 336	67.16 403	79.18 358	51.42 316	78.38 197	54.39 295	79.72 396	78.60 310

thres200		57.55 410	57.02 412	59.17 418	67.89 405	34.93 486	58.91 440	57.25 435	50.24 305	64.01 438	71.46 449	32.49 455	71.39 327	31.31 505	79.57 397	71.19 424

SP-DiffGlue		64.90 313	65.69 303	62.51 370	69.18 377	64.39 145	69.79 258	60.46 412	52.50 263	75.70 227	72.08 439	44.17 368	48.59 490	67.84 123	79.52 398	74.54 380

testgi		54.00 444	56.86 415	45.45 505	58.20 509	25.81 535	49.05 505	49.50 484	45.43 381	67.84 394	81.17 306	51.81 314	43.20 524	29.30 515	79.41 399	67.34 461

jason		64.47 323	62.84 349	69.34 252	76.91 215	59.20 205	67.15 323	65.67 370	35.29 489	65.16 420	76.74 386	44.67 364	70.68 334	54.74 289	79.28 400	78.14 321
jason: jason.
hybridnocas07		66.30 296	66.22 294	66.51 313	60.68 487	44.53 387	64.01 380	74.60 260	48.26 337	70.21 354	81.74 297	56.61 277	71.06 331	60.70 205	79.20 401	83.94 170

test_fmvsm_n_1920		69.63 226	68.45 251	73.16 150	70.56 349	65.86 128	70.26 249	78.35 208	37.69 471	74.29 270	78.89 363	61.10 211	68.10 371	65.87 144	79.07 402	85.53 109

Fast-Effi-MVS+-dtu		70.00 219	68.74 247	73.77 136	73.47 289	64.53 143	71.36 230	78.14 214	55.81 204	68.84 383	74.71 407	65.36 158	75.75 246	52.00 313	79.00 403	81.03 261

fmvsm_s_conf0.5_n_4		70.18 216	69.83 225	71.24 204	71.65 328	58.59 222	69.29 269	71.66 296	48.69 334	71.62 330	82.11 283	59.94 227	70.03 347	74.52 58	78.96 404	85.10 121

FBQ-MVS		59.22 392	57.87 402	63.30 357	73.18 295	39.68 442	68.92 279	63.38 392	45.87 374	60.72 469	69.03 480	27.40 498	73.66 287	33.33 495	78.95 405	76.57 348

EU-MVSNet		60.82 378	60.80 375	60.86 398	68.37 391	41.16 419	72.27 201	68.27 352	26.96 528	69.08 371	75.71 393	32.09 461	67.44 379	55.59 276	78.90 406	73.97 386

MVS_Test		69.84 223	70.71 212	67.24 297	67.49 412	43.25 402	69.87 256	81.22 141	52.69 261	71.57 336	86.68 168	62.09 194	74.51 268	66.05 141	78.74 407	83.96 168

Fast-Effi-MVS+		68.81 245	68.30 254	70.35 219	74.66 257	48.61 318	66.06 340	78.32 209	50.62 298	71.48 339	75.54 398	68.75 111	79.59 173	50.55 328	78.73 408	82.86 212

MVSFormer		69.93 221	69.03 241	72.63 177	74.93 246	59.19 206	83.98 45	75.72 248	52.27 267	63.53 449	76.74 386	43.19 377	80.56 155	72.28 84	78.67 409	78.14 321

lupinMVS		63.36 336	61.49 365	68.97 263	74.93 246	59.19 206	65.80 346	64.52 384	34.68 495	63.53 449	74.25 415	43.19 377	70.62 336	53.88 302	78.67 409	77.10 342

SP-NN		62.65 351	63.58 336	59.87 411	64.90 454	59.38 204	64.50 373	60.00 416	50.42 302	66.09 412	73.43 425	43.16 379	46.39 503	71.17 89	78.53 411	73.85 389

mvsmamba		68.87 243	67.30 276	73.57 142	76.58 223	53.70 265	84.43 42	74.25 263	45.38 382	76.63 205	84.55 219	35.85 434	85.27 60	49.54 337	78.49 412	81.75 250

Effi-MVS+		72.10 175	72.28 178	71.58 195	74.21 271	50.33 290	74.72 164	82.73 105	62.62 127	70.77 346	76.83 385	69.96 101	80.97 148	60.20 211	78.43 413	83.45 188

hybrid		65.62 303	65.49 306	66.01 319	60.48 489	44.28 390	64.13 376	74.21 264	46.41 366	69.84 363	80.86 313	55.77 286	70.28 343	59.30 228	78.42 414	83.46 186

CANet_DTU		64.04 329	63.83 331	64.66 333	68.39 389	42.97 405	73.45 184	74.50 262	52.05 273	54.78 505	75.44 401	43.99 369	70.42 340	53.49 306	78.41 415	80.59 277

myMVS_eth3d28		51.35 465	51.99 462	49.44 485	69.21 376	22.51 542	49.82 504	49.11 486	49.00 330	55.03 503	70.31 462	22.73 525	52.88 465	24.33 538	78.39 416	72.92 397

xiu_mvs_v1_base_debu		67.87 264	67.07 279	70.26 226	79.13 170	61.90 171	67.34 314	71.25 308	47.98 344	67.70 396	74.19 417	61.31 204	72.62 297	56.51 262	78.26 417	76.27 356

xiu_mvs_v1_base		67.87 264	67.07 279	70.26 226	79.13 170	61.90 171	67.34 314	71.25 308	47.98 344	67.70 396	74.19 417	61.31 204	72.62 297	56.51 262	78.26 417	76.27 356

xiu_mvs_v1_base_debi		67.87 264	67.07 279	70.26 226	79.13 170	61.90 171	67.34 314	71.25 308	47.98 344	67.70 396	74.19 417	61.31 204	72.62 297	56.51 262	78.26 417	76.27 356

fmvsm_l_conf0.5_n		67.48 270	66.88 287	69.28 253	67.41 413	62.04 169	70.69 242	69.85 324	39.46 455	69.59 366	81.09 309	58.15 256	68.73 361	67.51 126	78.16 420	77.07 345

BH-RMVSNet		68.69 250	68.20 260	70.14 231	76.40 226	53.90 264	64.62 369	73.48 269	58.01 168	73.91 283	81.78 293	59.09 242	78.22 202	48.59 350	77.96 421	78.31 316

RRT-MVS		70.33 210	70.73 211	69.14 257	71.93 325	45.24 375	75.10 154	75.08 256	60.85 142	78.62 154	87.36 143	49.54 330	78.64 187	60.16 213	77.90 422	83.55 180

IterMVS-SCA-FT		67.68 268	66.07 298	72.49 180	73.34 292	58.20 227	63.80 382	65.55 373	48.10 343	76.91 193	82.64 274	45.20 360	78.84 183	61.20 199	77.89 423	80.44 281

PVSNet_Blended		62.90 345	61.64 362	66.69 309	69.81 368	49.36 306	61.23 410	78.96 194	42.04 431	59.98 472	68.86 486	51.82 312	78.20 203	44.30 387	77.77 424	72.52 404

SD_0403		61.63 367	62.83 350	58.03 432	72.21 320	32.43 499	69.33 267	69.00 337	44.54 399	62.01 457	79.42 347	55.27 290	66.88 387	36.07 471	77.63 425	74.78 376

fmvsm_l_conf0.5_n_a		66.66 287	65.97 301	68.72 271	67.09 417	61.38 178	70.03 253	69.15 332	38.59 463	68.41 388	80.36 324	56.56 280	68.32 368	66.10 140	77.45 426	76.46 353

viewmambaseed2359dif		65.63 302	65.13 315	67.11 301	64.57 456	44.73 383	64.12 377	72.48 290	43.08 422	71.59 331	81.17 306	58.90 246	72.46 301	52.94 310	77.33 427	84.13 166

UWE-MVS		52.94 452	52.70 455	53.65 458	73.56 285	27.49 525	57.30 456	49.57 482	38.56 464	62.79 454	71.42 450	19.49 539	60.41 426	24.33 538	77.33 427	73.06 395

dtuplus		65.20 307	64.80 321	66.40 314	65.25 446	44.86 379	64.55 371	72.19 294	43.76 409	72.09 321	81.87 292	57.49 268	71.49 326	48.79 347	77.23 429	82.85 213

testing222		53.37 447	52.50 458	55.98 448	70.51 354	29.68 516	56.20 465	51.85 470	46.19 369	56.76 491	68.94 483	19.18 540	65.39 403	25.87 531	76.98 430	72.87 399

MSDG		67.47 272	67.48 271	67.46 293	70.70 345	54.69 257	66.90 329	78.17 212	60.88 141	70.41 350	74.76 405	61.22 209	73.18 289	47.38 363	76.87 431	74.49 382

testing91		55.74 429	55.29 438	57.08 440	70.63 346	30.85 510	54.94 476	56.31 448	50.34 303	57.08 487	70.10 467	24.50 515	65.86 399	36.98 458	76.75 432	74.53 381

XFeat-NN		44.60 499	44.89 501	43.74 513	46.61 545	44.56 384	41.07 529	40.59 538	23.40 540	66.73 407	54.97 531	20.65 531	40.41 535	33.52 494	76.49 433	46.25 535

E-PMN		45.17 494	45.36 497	44.60 509	50.07 538	42.75 406	38.66 535	42.29 528	46.39 367	39.55 545	51.15 536	26.00 506	45.37 512	37.68 449	76.41 434	45.69 537

PM-MVS		64.49 322	63.61 335	67.14 300	76.68 221	75.15 39	68.49 298	42.85 523	51.17 289	77.85 168	80.51 321	45.76 356	66.31 398	52.83 311	76.35 435	59.96 512

EIA-MVS		68.59 252	67.16 277	72.90 165	75.18 244	55.64 247	69.39 265	81.29 137	52.44 265	64.53 425	70.69 456	60.33 222	82.30 120	54.27 297	76.31 436	80.75 271

PRO-TEST		65.07 311	64.53 323	66.68 310	71.39 334	50.28 292	70.38 248	74.81 257	46.63 364	61.27 463	74.26 414	54.06 299	73.83 286	51.83 315	76.14 437	75.93 361

BH-w/o		64.81 316	64.29 327	66.36 315	76.08 233	54.71 256	65.61 349	75.23 253	50.10 308	71.05 345	71.86 446	54.33 296	79.02 180	38.20 443	76.14 437	65.36 482

testing99		55.16 435	54.56 445	56.98 442	70.13 364	30.58 512	54.55 479	54.11 456	49.53 317	56.76 491	70.14 466	22.76 524	65.79 401	36.99 457	76.04 439	74.57 379

MVS		60.62 381	59.97 382	62.58 369	68.13 399	47.28 342	68.59 293	73.96 266	32.19 506	59.94 474	68.86 486	50.48 323	77.64 214	41.85 411	75.74 440	62.83 497

TR-MVS		64.59 320	63.54 337	67.73 290	75.75 239	50.83 286	63.39 387	70.29 321	49.33 319	71.55 337	74.55 409	50.94 320	78.46 192	40.43 425	75.69 441	73.89 388

mvs_anonymous		65.08 310	65.49 306	63.83 343	63.79 462	37.60 465	66.52 335	69.82 325	43.44 415	73.46 292	86.08 193	58.79 248	71.75 322	51.90 314	75.63 442	82.15 235

QAPM		69.18 238	69.26 236	68.94 264	71.61 329	52.58 274	80.37 82	78.79 200	49.63 313	73.51 289	85.14 209	53.66 300	79.12 178	55.11 280	75.54 443	75.11 373

IterMVS		63.12 342	62.48 354	65.02 330	66.34 431	52.86 270	63.81 381	62.25 397	46.57 365	71.51 338	80.40 323	44.60 365	66.82 391	51.38 320	75.47 444	75.38 368
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		63.01 343	60.47 379	70.61 211	83.04 111	54.10 261	59.93 429	72.24 293	33.67 500	69.00 372	75.63 396	38.69 417	76.93 230	36.60 463	75.45 445	80.81 270

EMVS		44.61 498	44.45 504	45.10 508	48.91 541	43.00 404	37.92 536	41.10 536	46.75 361	38.00 547	48.43 541	26.42 502	46.27 504	37.11 456	75.38 446	46.03 536

MIMVSNet		54.39 439	56.12 424	49.20 486	72.57 312	30.91 509	59.98 427	48.43 492	41.66 435	55.94 497	83.86 242	41.19 399	50.42 474	26.05 528	75.38 446	66.27 473

our_test_3		56.46 422	56.51 418	56.30 445	67.70 408	39.66 443	55.36 472	52.34 469	40.57 450	63.85 440	69.91 470	40.04 407	58.22 444	43.49 394	75.29 448	71.03 427

pmmvs4		60.78 379	59.04 390	66.00 320	73.06 302	57.67 229	64.53 372	60.22 413	36.91 478	65.96 413	77.27 381	39.66 411	68.54 366	38.87 435	74.89 449	71.80 414

fmvsm_s_conf0.1_n_a		67.37 274	66.36 292	70.37 218	70.86 339	61.17 181	74.00 177	57.18 437	40.77 446	68.83 384	80.88 312	63.11 178	67.61 377	66.94 136	74.72 450	82.33 232

GA-MVS		62.91 344	61.66 361	66.66 311	67.09 417	44.49 388	61.18 412	69.36 330	51.33 285	69.33 370	74.47 410	36.83 429	74.94 262	50.60 327	74.72 450	80.57 278

KD-MVS_2432*1600		52.05 460	51.58 464	53.44 460	52.11 535	31.20 506	44.88 523	64.83 380	41.53 436	64.37 430	70.03 468	15.61 549	64.20 408	36.25 466	74.61 452	64.93 488

miper_refine_blended		52.05 460	51.58 464	53.44 460	52.11 535	31.20 506	44.88 523	64.83 380	41.53 436	64.37 430	70.03 468	15.61 549	64.20 408	36.25 466	74.61 452	64.93 488

fmvsm_s_conf0.5_n_a		67.00 285	65.95 302	70.17 229	69.72 372	61.16 182	73.34 186	56.83 440	40.96 443	68.36 389	80.08 332	62.84 180	67.57 378	66.90 138	74.50 454	81.78 248

fmvsm_s_conf0.1_n		66.60 288	65.54 305	69.77 243	68.99 383	59.15 209	72.12 205	56.74 442	40.72 448	68.25 393	80.14 331	61.18 210	66.92 384	67.34 133	74.40 455	83.23 197

pmmvs5		52.49 457	52.58 457	52.21 467	54.99 526	32.38 500	55.45 471	53.84 458	32.15 508	55.49 501	74.81 404	38.08 421	57.37 449	34.02 488	74.40 455	66.88 465

PatchT		53.35 448	56.47 419	43.99 512	64.19 459	17.46 548	59.15 434	43.10 520	52.11 272	54.74 506	86.95 152	29.97 487	49.98 479	43.62 392	74.40 455	64.53 492

fmvsm_s_conf0.5_n		66.34 295	65.27 309	69.57 247	68.20 395	59.14 211	71.66 224	56.48 443	40.92 444	67.78 395	79.46 345	61.23 207	66.90 385	67.39 129	74.32 458	82.66 221

SSC-MVS		61.79 364	66.08 296	48.89 490	76.91 215	10.00 556	53.56 483	47.37 497	68.20 67	76.56 209	89.21 97	54.13 297	57.59 448	54.75 288	74.07 459	79.08 303

xiu_mvs_v2_base		64.43 324	63.96 330	65.85 322	77.72 195	51.32 281	63.63 385	72.31 292	45.06 393	61.70 458	69.66 471	62.56 184	73.93 281	49.06 345	73.91 460	72.31 409

PS-MVSNAJ		64.27 327	63.73 333	65.90 321	77.82 193	51.42 279	63.33 388	72.33 291	45.09 392	61.60 459	68.04 491	62.39 188	73.95 280	49.07 344	73.87 461	72.34 408

OpenMVS_ROB	54.93 17	63.23 341	63.28 341	63.07 360	69.81 368	45.34 374	68.52 297	67.14 358	43.74 411	70.61 348	79.22 356	47.90 350	72.66 295	48.75 348	73.84 462	71.21 423

dtuonly		50.13 474	51.25 467	46.77 499	53.07 534	30.10 514	52.41 492	49.25 485	28.98 521	53.76 511	72.59 434	39.83 409	41.82 531	37.58 452	73.80 463	68.37 450

ETVMVS		50.32 472	49.87 480	51.68 470	70.30 360	26.66 528	52.33 493	43.93 514	43.54 414	54.91 504	67.95 492	20.01 537	60.17 429	22.47 541	73.40 464	68.22 453

test_fmvs3		56.78 419	55.99 427	59.12 420	53.96 532	48.09 324	58.76 441	66.22 366	27.54 524	76.66 204	68.69 488	25.32 511	51.31 468	53.42 308	73.38 465	77.97 326

MDTV_nov1_ep13			54.05 449		65.54 443	29.30 518	59.00 437	55.22 449	35.96 486	52.44 514	75.98 390	30.77 478	59.62 431	38.21 442	73.33 466

PAPM		61.79 364	60.37 380	66.05 318	76.09 231	41.87 412	69.30 268	76.79 235	40.64 449	53.80 510	79.62 343	44.38 366	82.92 105	29.64 514	73.11 467	73.36 393

WB-MVS		60.04 385	64.19 328	47.59 493	76.09 231	10.22 555	52.44 491	46.74 499	65.17 97	74.07 276	87.48 142	53.48 301	55.28 456	49.36 339	72.84 468	77.28 333

testing11		53.13 449	52.26 460	55.75 449	70.44 355	31.73 504	54.75 477	52.40 468	44.81 396	52.36 516	68.40 490	21.83 528	65.74 402	32.64 501	72.73 469	69.78 436

Patchmatch-test		47.93 485	49.96 479	41.84 517	57.42 514	24.26 537	48.75 506	41.49 531	39.30 458	56.79 490	73.48 423	30.48 482	33.87 542	29.29 516	72.61 470	67.39 459

gg-mvs-nofinetune		55.75 428	56.75 416	52.72 464	62.87 469	28.04 522	68.92 279	41.36 532	71.09 50	50.80 521	92.63 14	20.74 530	66.86 389	29.97 512	72.41 471	63.25 496

Syy-MVS		54.13 440	55.45 434	50.18 478	68.77 384	23.59 538	55.02 473	44.55 509	43.80 407	58.05 484	64.07 510	46.22 355	58.83 436	46.16 376	72.36 472	68.12 455

myMVS_eth3d		50.36 471	50.52 476	49.88 479	68.77 384	22.69 540	55.02 473	44.55 509	43.80 407	58.05 484	64.07 510	14.16 551	58.83 436	33.90 491	72.36 472	68.12 455

test_vis3_rt		51.94 462	51.04 470	54.65 453	46.32 546	50.13 294	44.34 525	78.17 212	23.62 539	68.95 375	62.81 515	21.41 529	38.52 539	41.49 413	72.22 474	75.30 370

test-LLR		50.43 470	50.69 475	49.64 482	60.76 485	41.87 412	53.18 485	45.48 505	43.41 417	49.41 526	60.47 524	29.22 491	44.73 516	42.09 408	72.14 475	62.33 505

test-mter		48.56 484	48.20 487	49.64 482	60.76 485	41.87 412	53.18 485	45.48 505	31.91 512	49.41 526	60.47 524	18.34 542	44.73 516	42.09 408	72.14 475	62.33 505

1112_ss		59.48 390	58.99 391	60.96 396	77.84 192	42.39 410	61.42 408	68.45 351	37.96 469	59.93 475	67.46 497	45.11 362	65.07 406	40.89 419	71.81 477	75.41 367

WB-MVSnew		53.94 445	54.76 443	51.49 472	71.53 330	28.05 521	58.22 450	50.36 478	37.94 470	59.16 479	70.17 465	49.21 335	51.94 467	24.49 536	71.80 478	74.47 383

MASt3R-SfM		45.75 490	47.16 491	41.50 520	47.00 544	47.91 329	45.50 520	38.10 541	21.81 546	73.91 283	62.86 514	29.14 493	29.95 547	34.59 484	71.54 479	46.65 533

UBG		49.18 481	49.35 481	48.66 491	70.36 358	26.56 530	50.53 500	45.61 503	37.43 474	53.37 512	65.97 504	23.03 523	54.20 460	26.29 526	71.54 479	65.20 485

PatchmatchNet1														28.98 521	71.38 481	62.61 501
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
N_pmnet		52.06 459	51.11 469	54.92 451	59.64 500	71.03 67	37.42 537	61.62 406	33.68 499	57.12 486	72.10 438	37.94 422	31.03 544	29.13 520	71.35 482	62.70 498

XXY-MVS		55.19 434	57.40 410	48.56 492	64.45 457	34.84 488	51.54 495	53.59 459	38.99 461	63.79 443	79.43 346	56.59 278	45.57 508	36.92 459	71.29 483	65.25 484

MDA-MVSNet_test_wron		52.57 456	53.49 452	49.81 481	54.24 528	36.47 472	40.48 532	46.58 500	38.13 466	75.47 236	73.32 427	41.05 402	43.85 522	40.98 418	71.20 484	69.10 446

YYNet1		52.58 455	53.50 450	49.85 480	54.15 529	36.45 473	40.53 531	46.55 501	38.09 467	75.52 233	73.31 428	41.08 401	43.88 521	41.10 416	71.14 485	69.21 444

nomal-1		49.95 476	49.18 483	52.26 465	57.73 512	44.81 380	46.14 519	49.57 482	37.60 473	56.41 495	65.96 505	24.21 517	52.60 466	33.97 489	71.04 486	59.37 514

HY-MVS	49.31 19	57.96 405	57.59 408	59.10 421	66.85 425	36.17 476	65.13 358	65.39 375	39.24 459	54.69 507	78.14 372	44.28 367	67.18 383	33.75 493	70.79 487	73.95 387

Test_1112_low_res		58.78 397	58.69 393	59.04 422	79.41 161	38.13 458	57.62 453	66.98 361	34.74 493	59.62 478	77.56 378	42.92 383	63.65 413	38.66 437	70.73 488	75.35 369

pmmvs3		46.71 488	45.09 499	51.55 471	56.76 517	48.25 320	55.78 469	39.53 540	24.13 538	50.35 524	63.40 512	15.90 548	51.08 470	29.29 516	70.69 489	55.33 522

test_fmvs2		54.80 437	54.11 448	56.88 443	51.76 537	49.95 297	56.70 459	65.80 369	26.22 531	69.42 368	65.25 508	31.82 466	49.98 479	49.63 336	70.36 490	70.71 428

SCA		58.57 401	58.04 401	60.17 409	70.17 361	41.07 421	65.19 357	53.38 463	43.34 419	61.00 467	73.48 423	45.20 360	69.38 357	40.34 426	70.31 491	70.05 432

CR-MVSNet		58.96 394	58.49 396	60.36 407	66.37 429	48.24 321	70.93 238	56.40 445	32.87 504	61.35 461	86.66 169	33.19 447	63.22 415	48.50 352	70.17 492	69.62 439

RPMNet		65.77 301	65.08 319	67.84 285	66.37 429	48.24 321	70.93 238	86.27 20	54.66 220	61.35 461	86.77 163	33.29 446	85.67 51	55.93 269	70.17 492	69.62 439

test0.0.03 1		47.72 486	48.31 485	45.93 503	55.53 524	29.39 517	46.40 517	41.21 535	43.41 417	55.81 499	67.65 496	29.22 491	43.77 523	25.73 533	69.87 494	64.62 490

PVSNet	43.83 21	51.56 463	51.17 468	52.73 463	68.34 392	38.27 455	48.22 508	53.56 461	36.41 481	54.29 508	64.94 509	34.60 439	54.20 460	30.34 509	69.87 494	65.71 477

tpm2		56.12 425	54.64 444	60.55 401	66.24 432	36.01 477	68.14 302	56.77 441	33.60 501	58.25 483	75.52 400	30.25 483	74.33 273	33.27 496	69.76 496	71.32 420

CostFormer		57.35 414	56.14 423	60.97 395	63.76 463	38.43 453	67.50 311	60.22 413	37.14 477	59.12 480	76.34 389	32.78 450	71.99 313	39.12 434	69.27 497	72.47 405

MonoMVSNet		62.75 348	63.42 338	60.73 399	65.60 441	40.77 426	72.49 198	70.56 318	52.49 264	75.07 248	79.42 347	39.52 413	69.97 349	46.59 371	69.06 498	71.44 418

baseline1		57.82 407	58.36 399	56.19 446	69.17 379	30.76 511	62.94 393	55.21 450	46.04 371	63.83 442	78.47 366	41.20 398	63.68 412	39.44 429	68.99 499	74.13 385

PatchMatch-RL		58.68 398	57.72 404	61.57 384	76.21 229	73.59 52	61.83 400	49.00 489	47.30 355	61.08 464	68.97 482	50.16 325	59.01 435	36.06 472	68.84 500	52.10 524

CVMVSNet		59.21 393	58.44 397	61.51 385	73.94 280	47.76 332	71.31 232	64.56 383	26.91 530	60.34 471	70.44 459	36.24 433	67.65 375	53.57 305	68.66 501	69.12 445

dmvs_re		49.91 477	50.77 474	47.34 494	59.98 493	38.86 450	53.18 485	53.58 460	39.75 453	55.06 502	61.58 520	36.42 432	44.40 519	29.15 519	68.23 502	58.75 516

TESTMET0.1,1		45.17 494	44.93 500	45.89 504	56.02 520	38.31 454	53.18 485	41.94 530	27.85 523	44.86 539	56.47 530	17.93 544	41.50 533	38.08 446	68.06 503	57.85 517

test_fmvs1_n		52.70 454	52.01 461	54.76 452	53.83 533	50.36 289	55.80 468	65.90 368	24.96 535	65.39 417	60.64 523	27.69 497	48.46 491	45.88 380	67.99 504	65.46 480

PMMVS2		37.74 509	40.87 508	28.36 528	42.41 551	5.35 561	24.61 545	27.75 550	32.15 508	47.85 531	70.27 463	35.85 434	29.51 548	19.08 546	67.85 505	50.22 528

1314		59.83 387	58.86 392	62.74 367	65.71 439	44.78 382	68.59 293	72.63 286	33.54 502	61.05 466	67.29 500	43.62 374	71.26 328	49.49 338	67.84 506	72.19 411

CHOSEN 1792x2688		58.09 404	56.30 420	63.45 354	79.95 153	50.93 285	54.07 481	65.59 372	28.56 522	61.53 460	74.33 412	41.09 400	66.52 396	33.91 490	67.69 507	72.92 397

0.4-1-1-0.1		51.02 467	48.31 485	59.15 419	60.95 484	37.94 462	53.17 489	59.12 423	39.52 454	47.88 530	50.31 539	20.36 535	69.99 348	35.79 473	67.66 508	69.51 441

test_fmvs1		51.51 464	50.86 473	53.48 459	49.72 540	49.35 308	54.11 480	64.96 378	24.64 537	63.66 446	59.61 527	28.33 496	48.45 492	45.38 385	67.30 509	62.66 500

0.4-1-1-0.2		49.48 479	46.57 493	58.21 429	58.02 511	36.93 469	50.24 502	59.18 421	37.97 468	44.94 537	46.16 543	20.52 532	69.54 355	34.84 482	67.28 510	68.17 454

0.3-1-1-0.015		49.68 478	46.67 492	58.69 425	58.94 504	37.51 467	51.35 497	59.18 421	38.35 465	44.62 541	47.14 542	18.49 541	69.68 353	35.13 479	66.84 511	68.87 447

tpm		50.60 469	52.42 459	45.14 507	65.18 448	26.29 531	60.30 423	43.50 517	37.41 475	57.01 488	79.09 360	30.20 485	42.32 526	32.77 500	66.36 512	66.81 467

FPMVS		59.43 391	60.07 381	57.51 438	77.62 198	71.52 62	62.33 397	50.92 475	57.40 177	69.40 369	80.00 333	39.14 415	61.92 421	37.47 453	66.36 512	39.09 543

GG-mvs-BLEND				52.24 466	60.64 488	29.21 519	69.73 259	42.41 525		45.47 535	52.33 535	20.43 534	68.16 370	25.52 534	65.42 514	59.36 515

UWE-MVS-28		44.18 500	44.37 505	43.61 514	60.10 491	16.96 549	52.62 490	33.27 548	36.79 479	48.86 528	69.47 477	19.96 538	45.65 507	13.40 548	64.83 515	68.23 452

tpmvs		55.84 427	55.45 434	57.01 441	60.33 490	33.20 497	65.89 343	59.29 420	47.52 352	56.04 496	73.60 422	31.05 475	68.06 372	40.64 424	64.64 516	69.77 437

WTY-MVS		49.39 480	50.31 478	46.62 501	61.22 482	32.00 503	46.61 516	49.77 480	33.87 498	54.12 509	69.55 475	41.96 388	45.40 511	31.28 506	64.42 517	62.47 502

baseline2		55.57 432	52.74 454	64.05 340	65.26 445	44.11 391	62.38 396	54.43 454	39.03 460	51.21 519	67.35 499	33.66 444	72.45 302	37.14 455	64.22 518	75.60 364

test_vis1_n		51.27 466	50.41 477	53.83 456	56.99 515	50.01 296	56.75 458	60.53 411	25.68 533	59.74 477	57.86 528	29.40 490	47.41 499	43.10 398	63.66 519	64.08 493

MS-PatchMatch		55.59 431	54.89 442	57.68 436	69.18 377	49.05 309	61.00 413	62.93 395	35.98 485	58.36 482	68.93 484	36.71 430	66.59 394	37.62 451	63.30 520	57.39 519

test_cas_vis1_n_1920		50.90 468	50.92 472	50.83 476	54.12 531	47.80 330	51.44 496	54.61 453	26.95 529	63.95 439	60.85 521	37.86 425	44.97 514	45.53 382	62.97 521	59.72 513

test_vis1_n_1920		52.96 451	53.50 450	51.32 473	59.15 502	44.90 378	56.13 466	64.29 386	30.56 517	59.87 476	60.68 522	40.16 406	47.47 498	48.25 356	62.46 522	61.58 507

test_f		43.79 502	45.63 495	38.24 525	42.29 552	38.58 452	34.76 542	47.68 495	22.22 544	67.34 401	63.15 513	31.82 466	30.60 546	39.19 433	62.28 523	45.53 538

sss		47.59 487	48.32 484	45.40 506	56.73 518	33.96 492	45.17 521	48.51 491	32.11 511	52.37 515	65.79 506	40.39 405	41.91 530	31.85 503	61.97 524	60.35 511

test_vis1_rt		46.70 489	45.24 498	51.06 475	44.58 547	51.04 284	39.91 533	67.56 356	21.84 545	51.94 517	50.79 537	33.83 442	39.77 536	35.25 477	61.50 525	62.38 503

PMMVS		44.69 496	43.95 506	46.92 497	50.05 539	53.47 267	48.08 510	42.40 526	22.36 543	44.01 543	53.05 534	42.60 386	45.49 509	31.69 504	61.36 526	41.79 540

blend_shiyan4		57.39 413	55.27 439	63.73 346	67.25 414	41.75 415	60.08 426	69.15 332	47.57 350	64.19 435	67.14 503	20.46 533	72.34 305	40.73 422	60.88 527	77.11 341

UnsupCasMVSNet_bld		50.01 475	51.03 471	46.95 496	58.61 506	32.64 498	48.31 507	53.27 464	34.27 496	60.47 470	71.53 448	41.40 396	47.07 501	30.68 508	60.78 528	61.13 509

MVP-Stereo		61.56 368	59.22 388	68.58 273	79.28 163	60.44 193	69.20 272	71.57 298	43.58 413	56.42 494	78.37 368	39.57 412	76.46 239	34.86 481	60.16 529	68.86 448
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
DSMNet-mixed		43.18 504	44.66 503	38.75 523	54.75 527	28.88 520	57.06 457	27.42 551	13.47 548	47.27 533	77.67 377	38.83 416	39.29 538	25.32 535	60.12 530	48.08 529

UnsupCasMVSNet_eth		52.26 458	53.29 453	49.16 487	55.08 525	33.67 495	50.03 503	58.79 425	37.67 472	63.43 451	74.75 406	41.82 392	45.83 506	38.59 439	59.42 531	67.98 458

tpm cat1		54.02 443	52.63 456	58.19 430	64.85 455	39.86 439	66.26 339	57.28 434	32.16 507	56.90 489	70.39 461	32.75 452	65.30 405	34.29 487	58.79 532	69.41 442

CHOSEN 280x420		41.62 505	39.89 510	46.80 498	61.81 478	51.59 277	33.56 543	35.74 545	27.48 525	37.64 549	53.53 532	23.24 521	42.09 528	27.39 524	58.64 533	46.72 532

tpmrst		50.15 473	51.38 466	46.45 502	56.05 519	24.77 536	64.40 375	49.98 479	36.14 484	53.32 513	69.59 474	35.16 437	48.69 488	39.24 432	58.51 534	65.89 475

PatchmatchNet		54.60 438	54.27 446	55.59 450	65.17 449	39.08 445	66.92 328	51.80 471	39.89 452	58.39 481	73.12 430	31.69 468	58.33 442	43.01 399	58.38 535	69.38 443
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MVS-HIRNet		45.53 492	47.29 489	40.24 521	62.29 476	26.82 527	56.02 467	37.41 543	29.74 520	43.69 544	81.27 304	33.96 441	55.48 455	24.46 537	56.79 536	38.43 544

ADS-MVSNet2		48.76 482	47.25 490	53.29 462	55.90 521	40.54 433	47.34 512	54.99 452	31.41 514	50.48 522	72.06 440	31.23 471	54.26 459	25.93 529	55.93 537	65.07 486

ADS-MVSNet		44.62 497	45.58 496	41.73 518	55.90 521	20.83 545	47.34 512	39.94 539	31.41 514	50.48 522	72.06 440	31.23 471	39.31 537	25.93 529	55.93 537	65.07 486

EPMVS		45.74 491	46.53 494	43.39 515	54.14 530	22.33 543	55.02 473	35.00 547	34.69 494	51.09 520	70.20 464	25.92 507	42.04 529	37.19 454	55.50 539	65.78 476

JIA-IIPM		54.03 442	51.62 463	61.25 392	59.14 503	55.21 254	59.10 436	47.72 494	50.85 294	50.31 525	85.81 200	20.10 536	63.97 410	36.16 469	55.41 540	64.55 491

dmvs_testset		45.26 493	47.51 488	38.49 524	59.96 495	14.71 551	58.50 448	43.39 519	41.30 438	51.79 518	56.48 529	39.44 414	49.91 481	21.42 543	55.35 541	50.85 526

new_pmnet		37.55 510	39.80 511	30.79 527	56.83 516	16.46 550	39.35 534	30.65 549	25.59 534	45.26 536	61.60 519	24.54 514	28.02 549	21.60 542	52.80 542	47.90 530

dp		44.09 501	44.88 502	41.72 519	58.53 508	23.18 539	54.70 478	42.38 527	34.80 492	44.25 542	65.61 507	24.48 516	44.80 515	29.77 513	49.42 543	57.18 520

mvsany_test3		43.76 503	41.01 507	52.01 468	48.09 542	57.74 228	42.47 527	23.85 554	23.30 541	64.80 424	62.17 518	27.12 499	40.59 534	29.17 518	48.11 544	57.69 518

MVE	27.91 23	36.69 511	35.64 514	39.84 522	43.37 550	35.85 480	19.49 546	24.61 552	24.68 536	39.05 546	62.63 517	38.67 418	27.10 550	21.04 544	47.25 545	56.56 521
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GLUNet-SfM		24.03 513	24.76 516	21.84 530	12.84 556	18.20 547	27.35 544	15.92 556	9.48 549	63.07 453	34.11 546	10.20 555	23.13 552	9.60 552	40.26 546	24.18 547

mvsany_test1		37.88 508	35.74 513	44.28 510	47.28 543	49.90 298	36.54 539	24.37 553	19.56 547	45.76 534	53.46 533	32.99 449	37.97 540	26.17 527	35.52 547	44.99 539

PVSNet_0	36.71 22	41.12 506	40.78 509	42.14 516	59.97 494	40.13 436	40.97 530	42.24 529	30.81 516	44.86 539	49.41 540	40.70 403	45.12 513	23.15 540	34.96 548	41.16 542

tmp_tt		11.98 517	14.73 520	3.72 536	2.28 560	4.62 562	19.44 547	14.50 557	0.47 555	21.55 551	9.58 552	25.78 508	4.57 556	11.61 550	27.37 549	1.96 552

test_method		19.26 515	19.12 519	19.71 531	9.09 558	1.91 563	7.79 548	53.44 462	1.42 553	10.27 555	35.80 545	17.42 546	25.11 551	12.44 549	24.38 550	32.10 545

dongtai		31.66 512	32.98 515	27.71 529	58.58 507	12.61 553	45.02 522	14.24 558	41.90 433	47.93 529	43.91 544	10.65 554	41.81 532	14.06 547	20.53 551	28.72 546

kuosan		22.02 514	23.52 518	17.54 532	41.56 553	11.24 554	41.99 528	13.39 559	26.13 532	28.87 550	30.75 547	9.72 556	21.94 553	4.77 554	14.49 552	19.43 548

VLMVS_CLIP		7.76 519	8.41 522	5.81 534	6.67 559	5.99 560	6.46 550	9.96 561	2.09 551	12.33 554	14.87 550	5.07 558	8.68 555	4.33 555	13.87 553	2.74 551

DeepMVS_CX				11.83 533	15.51 555	13.86 552		11.25 560	5.76 550	20.85 552	26.46 548	17.06 547	9.22 554	9.69 551	13.82 554	12.42 549

MVS_clip		7.93 518	9.12 521	4.36 535	9.81 557	6.92 558	6.89 549	1.72 562	1.89 552	16.36 553	21.19 549	4.56 559	2.56 557	6.56 553	13.13 555	3.60 550

MVS_baseline		2.33 524	2.94 527	0.51 538	2.02 561	0.19 566	1.06 551	0.36 565	0.07 559	6.71 556	7.92 553	1.17 561	0.00 561	0.96 556	6.20 556	1.34 554

VLMVS		1.59 525	1.75 528	1.12 537	1.56 562	1.00 564	0.99 552	0.58 563	0.08 558	2.81 557	3.50 554	2.79 560	0.76 558	0.70 557	2.74 557	1.60 553

test123		4.43 522	5.78 525	0.39 540	0.97 563	0.28 565	46.33 518	0.45 564	0.31 556	0.62 559	1.50 557	0.61 563	0.11 560	0.56 558	0.63 558	0.77 556

testmvs		4.06 523	5.28 526	0.41 539	0.64 564	0.16 567	42.54 526	0.31 566	0.26 557	0.50 560	1.40 558	0.77 562	0.17 559	0.56 558	0.55 559	0.90 555

mmdepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

monomultidepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

test_blank		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uanet_test		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

DCPMVS		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

cdsmvs_eth3d_5k		17.71 516	23.62 517	0.00 541	0.00 565	0.00 568	0.00 553	70.17 322	0.00 560	0.00 561	74.25 415	68.16 119	0.00 561	0.00 560	0.00 560	0.00 557

pcd_1.5k_mvsjas		5.20 521	6.93 524	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	62.39 188	0.00 561	0.00 560	0.00 560	0.00 557

sosnet-low-res		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

sosnet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uncertanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

Regformer		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

ab-mvs-re		5.62 520	7.50 523	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	67.46 497	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

PatchmatchNet2					0.00 565	8.37 557	35.35 541	35.51 546	32.14 510
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													30.98 545
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						22.69 540								36.10 470

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

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

eth-test2					0.00 565

eth-test					0.00 565

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 48

save fliter					87.00 39	67.23 111	79.24 97	77.94 217	56.65 191

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

GSMVS																70.05 432

test_part2					85.90 62	66.44 121				84.61 75

sam_mvs1												31.41 469				70.05 432

sam_mvs												31.21 473

MTGPA								80.63 157

test_post1							66.63 332				2.08 555	30.66 481	59.33 433	40.34 426

test_post											1.99 556	30.91 476	54.76 458

patchmatchnet-post											68.99 481	31.32 470	69.38 357

MTMP							84.83 38	19.26 555

gm-plane-assit					62.51 473	33.91 494			37.25 476		62.71 516		72.74 293	38.70 436

TEST9					85.47 69	69.32 87	76.42 135	78.69 202	53.73 245	76.97 190	86.74 164	66.84 136	81.10 142

test_8					85.09 76	67.89 100	76.26 142	78.66 204	54.00 240	76.89 194	86.72 167	66.60 142	80.89 152

agg_prior					84.44 89	66.02 127		78.62 205		76.95 192			80.34 160

test_prior4						70.14 78	77.57 115

test_prior				75.27 116	82.15 126	59.85 201		84.33 73					83.39 97			82.58 223

旧先验2							71.17 235		45.11 391	78.54 158			61.28 424	59.19 230

新几何2							71.33 231

无先验							74.82 158	70.94 315	47.75 349				76.85 234	54.47 292		72.09 412

原ACMM2							74.78 162

testdata2													67.30 380	48.34 354

segment_acmp												68.30 118

testdata1							68.34 301		57.24 180

plane_prior7					85.18 72	66.21 124

plane_prior6					84.18 93	65.31 135						60.83 214

plane_prior4											89.11 102

plane_prior3						65.67 130			63.82 112	78.23 162

plane_prior2							82.74 61		65.45 89

plane_prior1					84.46 88

n2								0.00 567

nn								0.00 567

door-mid								55.02 451

test11								82.71 106

door								52.91 466

HQP5-MVS						58.80 217

HQP-NCC					82.37 120		77.32 120		59.08 153	71.58 333

ACMP_Plane					82.37 120		77.32 120		59.08 153	71.58 333

BP-MVS														67.38 131

HQP4-MVS										71.59 331			85.31 58			83.74 176

HQP2-MVS												58.09 258

NP-MVS					83.34 105	63.07 163					85.97 196

MDTV_nov1_ep13_2view						18.41 546	53.74 482		31.57 513	44.89 538		29.90 488		32.93 499		71.48 417

Test By Simon												62.56 184

High-resolution multi-view benchmark