High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		95.70 1	96.40 1	93.61 3	98.67 1	85.39 37	95.54 5	97.36 1	96.97 1	99.04 1	99.05 1	96.61 1	95.92 16	85.07 61	99.27 1	99.54 1

mamv4		95.37 2	94.51 2	97.96 1	96.31 10	98.41 1	91.05 46	97.23 2	95.32 2	99.01 2	97.26 6	80.16 134	98.99 1	95.15 1	99.14 2	96.47 30

WR-MVS_H		89.91 50	91.31 33	85.71 128	96.32 9	62.39 267	89.54 79	93.31 70	90.21 12	95.57 11	95.66 33	81.42 120	95.90 17	80.94 106	98.80 3	98.84 5

ACMP	79.16 10	90.54 35	90.60 49	90.35 45	94.36 46	80.98 69	89.16 86	94.05 41	79.03 108	92.87 49	93.74 111	90.60 11	95.21 61	82.87 85	98.76 4	94.87 70
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMH+	77.89 11	90.73 31	91.50 25	88.44 78	93.00 81	76.26 119	89.65 75	95.55 8	87.72 26	93.89 30	94.94 52	91.62 3	93.44 128	78.35 136	98.76 4	95.61 50

PS-CasMVS		90.06 43	91.92 15	84.47 153	96.56 6	58.83 314	89.04 88	92.74 97	91.40 6	96.12 5	96.06 26	87.23 48	95.57 41	79.42 126	98.74 6	99.00 2

LPG-MVS_test		91.47 21	91.68 20	90.82 37	94.75 41	81.69 63	90.00 62	94.27 24	82.35 68	93.67 37	94.82 56	91.18 4	95.52 45	85.36 58	98.73 7	95.23 61

LGP-MVS_train				90.82 37	94.75 41	81.69 63		94.27 24	82.35 68	93.67 37	94.82 56	91.18 4	95.52 45	85.36 58	98.73 7	95.23 61

PEN-MVS		90.03 45	91.88 18	84.48 152	96.57 5	58.88 311	88.95 89	93.19 75	91.62 5	96.01 7	96.16 24	87.02 50	95.60 40	78.69 132	98.72 9	98.97 3

CP-MVSNet		89.27 62	90.91 44	84.37 154	96.34 8	58.61 317	88.66 97	92.06 116	90.78 7	95.67 8	95.17 47	81.80 116	95.54 44	79.00 130	98.69 10	98.95 4

TranMVSNet+NR-MVSNet		87.86 81	88.76 74	85.18 136	94.02 58	64.13 243	84.38 173	91.29 140	84.88 44	92.06 65	93.84 105	86.45 58	93.73 111	73.22 205	98.66 11	97.69 9

NR-MVSNet		86.00 108	86.22 108	85.34 134	93.24 76	64.56 239	82.21 235	90.46 162	80.99 82	88.42 137	91.97 165	77.56 156	93.85 107	72.46 215	98.65 12	97.61 10

UA-Net		91.49 19	91.53 24	91.39 27	94.98 35	82.95 58	93.52 7	92.79 95	88.22 22	88.53 133	97.64 3	83.45 86	94.55 83	86.02 53	98.60 13	96.67 25

FC-MVSNet-test		85.93 110	87.05 95	82.58 209	92.25 101	56.44 333	85.75 146	93.09 81	77.33 130	91.94 68	94.65 61	74.78 190	93.41 130	75.11 181	98.58 14	97.88 7

DTE-MVSNet		89.98 47	91.91 17	84.21 162	96.51 7	57.84 322	88.93 90	92.84 94	91.92 4	96.16 4	96.23 21	86.95 51	95.99 12	79.05 129	98.57 15	98.80 6

UniMVSNet (Re)		86.87 91	86.98 97	86.55 106	93.11 79	68.48 202	83.80 188	92.87 92	80.37 87	89.61 113	91.81 173	77.72 154	94.18 95	75.00 182	98.53 16	96.99 22

Baseline_NR-MVSNet		84.00 154	85.90 115	78.29 278	91.47 134	53.44 356	82.29 231	87.00 236	79.06 107	89.55 115	95.72 32	77.20 161	86.14 300	72.30 216	98.51 17	95.28 58

TDRefinement		93.52 3	93.39 4	93.88 2	95.94 15	90.26 4	95.70 4	96.46 3	90.58 9	92.86 50	96.29 19	88.16 35	94.17 97	86.07 49	98.48 18	97.22 17

ACMM	79.39 9	90.65 32	90.99 41	89.63 57	95.03 34	83.53 51	89.62 76	93.35 66	79.20 105	93.83 31	93.60 116	90.81 7	92.96 144	85.02 63	98.45 19	92.41 179
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MP-MVS-pluss		90.81 30	91.08 37	89.99 50	95.97 14	79.88 75	88.13 102	94.51 18	75.79 147	92.94 47	94.96 51	88.36 30	95.01 68	90.70 3	98.40 20	95.09 66
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CP-MVS		91.67 16	91.58 23	91.96 14	95.29 31	87.62 13	93.38 9	93.36 65	83.16 60	91.06 82	94.00 95	88.26 32	95.71 37	87.28 31	98.39 21	92.55 172

UniMVSNet_NR-MVSNet		86.84 93	87.06 94	86.17 118	92.86 86	67.02 216	82.55 223	91.56 130	83.08 62	90.92 84	91.82 172	78.25 148	93.99 102	74.16 187	98.35 22	97.49 13

DU-MVS		86.80 94	86.99 96	86.21 116	93.24 76	67.02 216	83.16 206	92.21 111	81.73 74	90.92 84	91.97 165	77.20 161	93.99 102	74.16 187	98.35 22	97.61 10

MTAPA		91.52 18	91.60 22	91.29 30	96.59 4	86.29 21	92.02 33	91.81 127	84.07 49	92.00 66	94.40 76	86.63 54	95.28 58	88.59 10	98.31 24	92.30 186

ACMH	76.49 14	89.34 59	91.14 35	83.96 167	92.50 94	70.36 180	89.55 77	93.84 52	81.89 73	94.70 17	95.44 40	90.69 8	88.31 265	83.33 77	98.30 25	93.20 145
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
reproduce_model		92.89 5	93.18 7	92.01 13	94.20 49	88.23 9	92.87 13	94.32 21	90.25 11	95.65 9	95.74 30	87.75 41	95.72 36	89.60 4	98.27 26	92.08 197

COLMAP_ROB	83.01 3	91.97 13	91.95 14	92.04 11	93.68 65	86.15 24	93.37 10	95.10 13	90.28 10	92.11 63	95.03 50	89.75 20	94.93 70	79.95 117	98.27 26	95.04 67
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
reproduce-ours		92.86 6	93.22 5	91.76 23	94.39 44	87.71 11	92.40 27	94.38 19	89.82 13	95.51 12	95.49 38	89.64 21	95.82 26	89.13 6	98.26 28	91.76 208

our_new_method		92.86 6	93.22 5	91.76 23	94.39 44	87.71 11	92.40 27	94.38 19	89.82 13	95.51 12	95.49 38	89.64 21	95.82 26	89.13 6	98.26 28	91.76 208

ACMMP		91.91 14	91.87 19	92.03 12	95.53 27	85.91 28	93.35 11	94.16 32	82.52 67	92.39 61	94.14 89	89.15 25	95.62 39	87.35 28	98.24 30	94.56 80
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
HPM-MVS		92.13 11	92.20 13	91.91 17	95.58 26	84.67 46	93.51 8	94.85 15	82.88 64	91.77 70	93.94 102	90.55 12	95.73 35	88.50 11	98.23 31	95.33 56
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test_0728_THIRD									85.33 38	93.75 34	94.65 61	87.44 46	95.78 32	87.41 26	98.21 32	92.98 156

MP-MVS		91.14 28	90.91 44	91.83 20	96.18 11	86.88 17	92.20 30	93.03 86	82.59 66	88.52 134	94.37 78	86.74 53	95.41 53	86.32 43	98.21 32	93.19 146
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SteuartSystems-ACMMP		91.16 27	91.36 28	90.55 41	93.91 60	80.97 70	91.49 40	93.48 63	82.82 65	92.60 57	93.97 96	88.19 33	96.29 6	87.61 21	98.20 34	94.39 91
Skip Steuart: Steuart Systems R&D Blog.
MSC_two_6792asdad				88.81 71	91.55 129	77.99 94		91.01 148					96.05 9	87.45 24	98.17 35	92.40 181

No_MVS				88.81 71	91.55 129	77.99 94		91.01 148					96.05 9	87.45 24	98.17 35	92.40 181

HPM-MVS_fast		92.50 8	92.54 9	92.37 6	95.93 16	85.81 33	92.99 12	94.23 27	85.21 40	92.51 58	95.13 48	90.65 9	95.34 55	88.06 13	98.15 37	95.95 41

mPP-MVS		91.69 15	91.47 26	92.37 6	96.04 13	88.48 8	92.72 18	92.60 102	83.09 61	91.54 72	94.25 83	87.67 44	95.51 47	87.21 32	98.11 38	93.12 150

WR-MVS		83.56 166	84.40 150	81.06 237	93.43 70	54.88 346	78.67 286	85.02 266	81.24 79	90.74 90	91.56 180	72.85 216	91.08 195	68.00 258	98.04 39	97.23 16

XVG-ACMP-BASELINE		89.98 47	89.84 54	90.41 43	94.91 37	84.50 48	89.49 81	93.98 43	79.68 97	92.09 64	93.89 104	83.80 81	93.10 140	82.67 89	98.04 39	93.64 127

DeepC-MVS	82.31 4	89.15 64	89.08 66	89.37 62	93.64 66	79.07 83	88.54 98	94.20 30	73.53 175	89.71 107	94.82 56	85.09 68	95.77 34	84.17 72	98.03 41	93.26 143
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FIs		85.35 119	86.27 107	82.60 208	91.86 116	57.31 326	85.10 160	93.05 83	75.83 146	91.02 83	93.97 96	73.57 204	92.91 148	73.97 193	98.02 42	97.58 12

Anonymous20231211		88.40 71	89.62 59	84.73 145	90.46 157	65.27 232	88.86 91	93.02 87	87.15 28	93.05 46	97.10 8	82.28 105	92.02 170	76.70 160	97.99 43	96.88 23

PGM-MVS		91.20 26	90.95 43	91.93 15	95.67 23	85.85 31	90.00 62	93.90 48	80.32 89	91.74 71	94.41 75	88.17 34	95.98 13	86.37 42	97.99 43	93.96 108

APDe-MVS		91.22 25	91.92 15	89.14 66	92.97 82	78.04 93	92.84 16	94.14 36	83.33 58	93.90 28	95.73 31	88.77 27	96.41 3	87.60 22	97.98 45	92.98 156
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		90.06 43	91.32 32	86.29 111	94.16 53	72.56 151	90.54 52	91.01 148	83.61 55	93.75 34	94.65 61	89.76 18	95.78 32	86.42 40	97.97 46	90.55 244
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				86.79 102	94.25 48	72.45 155	90.54 52	94.10 39					95.88 18	86.42 40	97.97 46	92.02 200

ZNCC-MVS		91.26 24	91.34 31	91.01 34	95.73 21	83.05 56	92.18 31	94.22 29	80.14 92	91.29 78	93.97 96	87.93 40	95.87 20	88.65 9	97.96 48	94.12 103

SED-MVS		90.46 37	91.64 21	86.93 99	94.18 50	72.65 145	90.47 55	93.69 56	83.77 52	94.11 26	94.27 79	90.28 14	95.84 24	86.03 50	97.92 49	92.29 187

IU-MVS					94.18 50	72.64 147		90.82 153	56.98 351	89.67 109				85.78 55	97.92 49	93.28 141

CLD-MVS		83.18 173	82.64 181	84.79 143	89.05 184	67.82 210	77.93 294	92.52 103	68.33 245	85.07 211	81.54 355	82.06 109	92.96 144	69.35 240	97.91 51	93.57 132
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IS-MVSNet		86.66 97	86.82 101	86.17 118	92.05 109	66.87 219	91.21 43	88.64 204	86.30 33	89.60 114	92.59 146	69.22 245	94.91 71	73.89 194	97.89 52	96.72 24

ACMMP_NAP		90.65 32	91.07 39	89.42 61	95.93 16	79.54 80	89.95 66	93.68 58	77.65 126	91.97 67	94.89 53	88.38 29	95.45 51	89.27 5	97.87 53	93.27 142

test_241102_TWO								93.71 55	83.77 52	93.49 39	94.27 79	89.27 23	95.84 24	86.03 50	97.82 54	92.04 199

DPE-MVS		90.53 36	91.08 37	88.88 69	93.38 71	78.65 87	89.15 87	94.05 41	84.68 45	93.90 28	94.11 91	88.13 36	96.30 5	84.51 69	97.81 55	91.70 212
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
OurMVSNet-221017-0		90.01 46	89.74 56	90.83 36	93.16 78	80.37 72	91.91 36	93.11 79	81.10 81	95.32 14	97.24 7	72.94 215	94.85 72	85.07 61	97.78 56	97.26 15

SMA-MVS		90.31 38	90.48 50	89.83 54	95.31 30	79.52 81	90.98 47	93.24 74	75.37 156	92.84 51	95.28 44	85.58 67	96.09 8	87.92 15	97.76 57	93.88 112
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
ACMMPR		91.49 19	91.35 30	91.92 16	95.74 20	85.88 30	92.58 22	93.25 73	81.99 70	91.40 74	94.17 88	87.51 45	95.87 20	87.74 17	97.76 57	93.99 106

HFP-MVS		91.30 23	91.39 27	91.02 33	95.43 29	84.66 47	92.58 22	93.29 72	81.99 70	91.47 73	93.96 99	88.35 31	95.56 42	87.74 17	97.74 59	92.85 159

region2R		91.44 22	91.30 34	91.87 19	95.75 19	85.90 29	92.63 21	93.30 71	81.91 72	90.88 88	94.21 84	87.75 41	95.87 20	87.60 22	97.71 60	93.83 115

GST-MVS		90.96 29	91.01 40	90.82 37	95.45 28	82.73 59	91.75 38	93.74 54	80.98 83	91.38 75	93.80 106	87.20 49	95.80 28	87.10 35	97.69 61	93.93 109

UniMVSNet_ETH3D		89.12 65	90.72 47	84.31 160	97.00 2	64.33 242	89.67 74	88.38 207	88.84 17	94.29 22	97.57 4	90.48 13	91.26 189	72.57 214	97.65 62	97.34 14

v7n		90.13 40	90.96 42	87.65 91	91.95 112	71.06 173	89.99 64	93.05 83	86.53 31	94.29 22	96.27 20	82.69 93	94.08 100	86.25 46	97.63 63	97.82 8

XVS		91.54 17	91.36 28	92.08 9	95.64 24	86.25 22	92.64 19	93.33 67	85.07 41	89.99 100	94.03 93	86.57 55	95.80 28	87.35 28	97.62 64	94.20 96

X-MVStestdata		85.04 126	82.70 179	92.08 9	95.64 24	86.25 22	92.64 19	93.33 67	85.07 41	89.99 100	16.05 424	86.57 55	95.80 28	87.35 28	97.62 64	94.20 96

SR-MVS-dyc-post		92.41 9	92.41 10	92.39 5	94.13 55	88.95 6	92.87 13	94.16 32	88.75 18	93.79 32	94.43 72	88.83 26	95.51 47	87.16 33	97.60 66	92.73 162

RE-MVS-def			92.61 8		94.13 55	88.95 6	92.87 13	94.16 32	88.75 18	93.79 32	94.43 72	90.64 10		87.16 33	97.60 66	92.73 162

APD-MVS_3200maxsize		92.05 12	92.24 12	91.48 25	93.02 80	85.17 39	92.47 26	95.05 14	87.65 27	93.21 43	94.39 77	90.09 17	95.08 66	86.67 39	97.60 66	94.18 99

Anonymous20240521		80.18 230	81.25 207	76.95 297	83.15 319	60.84 290	82.46 226	85.99 249	68.76 240	86.78 173	93.73 112	59.13 302	77.44 364	73.71 198	97.55 69	92.56 171

9.14			89.29 62		91.84 119		88.80 93	95.32 12	75.14 158	91.07 81	92.89 136	87.27 47	93.78 110	83.69 76	97.55 69

OPM-MVS		89.80 51	89.97 52	89.27 63	94.76 40	79.86 76	86.76 127	92.78 96	78.78 111	92.51 58	93.64 115	88.13 36	93.84 109	84.83 66	97.55 69	94.10 104
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LTVRE_ROB	86.10 1	93.04 4	93.44 3	91.82 22	93.73 64	85.72 34	96.79 1	95.51 9	88.86 16	95.63 10	96.99 10	84.81 72	93.16 137	91.10 2	97.53 72	96.58 28
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
SF-MVS		90.27 39	90.80 46	88.68 76	92.86 86	77.09 108	91.19 44	95.74 6	81.38 78	92.28 62	93.80 106	86.89 52	94.64 78	85.52 57	97.51 73	94.30 95

MIMVSNet1		83.63 163	84.59 142	80.74 241	94.06 57	62.77 260	82.72 217	84.53 275	77.57 128	90.34 93	95.92 28	76.88 173	85.83 308	61.88 309	97.42 74	93.62 128

ACMMP++															97.35 75

SR-MVS		92.23 10	92.34 11	91.91 17	94.89 38	87.85 10	92.51 24	93.87 51	88.20 23	93.24 42	94.02 94	90.15 16	95.67 38	86.82 37	97.34 76	92.19 193

nrg030		87.85 82	88.49 75	85.91 122	90.07 166	69.73 186	87.86 106	94.20 30	74.04 167	92.70 56	94.66 60	85.88 66	91.50 181	79.72 120	97.32 77	96.50 29

pmmvs6		86.52 99	88.06 79	81.90 219	92.22 103	62.28 270	84.66 166	89.15 198	83.54 57	89.85 104	97.32 5	88.08 38	86.80 286	70.43 231	97.30 78	96.62 26

SD-MVS		88.96 67	89.88 53	86.22 115	91.63 123	77.07 109	89.82 69	93.77 53	78.90 109	92.88 48	92.29 159	86.11 63	90.22 222	86.24 47	97.24 79	91.36 220
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
CPTT-MVS		89.39 58	88.98 69	90.63 40	95.09 33	86.95 16	92.09 32	92.30 110	79.74 96	87.50 160	92.38 153	81.42 120	93.28 133	83.07 81	97.24 79	91.67 213

APD-MVS		89.54 56	89.63 58	89.26 64	92.57 91	81.34 68	90.19 61	93.08 82	80.87 85	91.13 80	93.19 122	86.22 62	95.97 14	82.23 95	97.18 81	90.45 246
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
wuyk23d		75.13 283	79.30 236	62.63 388	75.56 388	75.18 126	80.89 253	73.10 359	75.06 159	94.76 16	95.32 41	87.73 43	52.85 419	34.16 418	97.11 82	59.85 415

PMVS	80.48 6	90.08 41	90.66 48	88.34 81	96.71 3	92.97 2	90.31 59	89.57 193	88.51 21	90.11 96	95.12 49	90.98 6	88.92 254	77.55 150	97.07 83	83.13 356
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
OMC-MVS		88.19 74	87.52 85	90.19 48	91.94 114	81.68 65	87.49 112	93.17 76	76.02 141	88.64 130	91.22 188	84.24 78	93.37 131	77.97 146	97.03 84	95.52 51

test_prior2							83.37 198		75.43 154	84.58 221	91.57 179	81.92 114		79.54 124	96.97 85

EPP-MVSNet		85.47 116	85.04 133	86.77 103	91.52 132	69.37 190	91.63 39	87.98 216	81.51 77	87.05 170	91.83 171	66.18 260	95.29 56	70.75 226	96.89 86	95.64 48

VDDNet		84.35 141	85.39 128	81.25 232	95.13 32	59.32 304	85.42 153	81.11 303	86.41 32	87.41 161	96.21 22	73.61 203	90.61 214	66.33 269	96.85 87	93.81 119

VPNet		80.25 227	81.68 194	75.94 311	92.46 95	47.98 386	76.70 314	81.67 299	73.45 177	84.87 217	92.82 139	74.66 193	86.51 291	61.66 312	96.85 87	93.33 138

SixPastTwentyTwo		87.20 89	87.45 87	86.45 108	92.52 93	69.19 195	87.84 107	88.05 214	81.66 75	94.64 18	96.53 17	65.94 261	94.75 74	83.02 83	96.83 89	95.41 53

VPA-MVSNet		83.47 169	84.73 137	79.69 257	90.29 160	57.52 325	81.30 247	88.69 203	76.29 137	87.58 159	94.44 71	80.60 130	87.20 278	66.60 267	96.82 90	94.34 93

Gipuma		84.44 139	86.33 106	78.78 267	84.20 297	73.57 135	89.55 77	90.44 163	84.24 48	84.38 226	94.89 53	76.35 178	80.40 350	76.14 169	96.80 91	82.36 366
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ZD-MVS					92.22 103	80.48 71		91.85 123	71.22 215	90.38 92	92.98 131	86.06 64	96.11 7	81.99 98	96.75 92

CDPH-MVS		86.17 107	85.54 124	88.05 86	92.25 101	75.45 124	83.85 185	92.01 117	65.91 270	86.19 189	91.75 176	83.77 82	94.98 69	77.43 153	96.71 93	93.73 122

KD-MVS_self_test		81.93 199	83.14 172	78.30 277	84.75 286	52.75 360	80.37 259	89.42 196	70.24 227	90.26 95	93.39 119	74.55 195	86.77 287	68.61 253	96.64 94	95.38 54

DP-MVS		88.60 70	89.01 67	87.36 93	91.30 136	77.50 101	87.55 109	92.97 90	87.95 25	89.62 111	92.87 137	84.56 73	93.89 106	77.65 148	96.62 95	90.70 238

TransMVSNet (Re)		84.02 153	85.74 121	78.85 266	91.00 146	55.20 345	82.29 231	87.26 223	79.65 98	88.38 139	95.52 37	83.00 90	86.88 284	67.97 259	96.60 96	94.45 86

ambc				82.98 197	90.55 156	64.86 236	88.20 100	89.15 198		89.40 118	93.96 99	71.67 233	91.38 188	78.83 131	96.55 97	92.71 165

train_agg		85.98 109	85.28 130	88.07 85	92.34 98	79.70 78	83.94 181	90.32 169	65.79 272	84.49 223	90.97 197	81.93 112	93.63 115	81.21 103	96.54 98	90.88 232

VDD-MVS		84.23 147	84.58 143	83.20 191	91.17 142	65.16 235	83.25 202	84.97 269	79.79 95	87.18 163	94.27 79	74.77 191	90.89 203	69.24 241	96.54 98	93.55 135

HPM-MVS++		88.93 68	88.45 76	90.38 44	94.92 36	85.85 31	89.70 71	91.27 141	78.20 118	86.69 178	92.28 160	80.36 132	95.06 67	86.17 48	96.49 100	90.22 250

test_djsdf		89.62 54	89.01 67	91.45 26	92.36 97	82.98 57	91.98 34	90.08 180	71.54 209	94.28 24	96.54 16	81.57 118	94.27 89	86.26 44	96.49 100	97.09 19

SPE-MVS-test		87.00 90	86.43 105	88.71 74	89.46 176	77.46 102	89.42 84	95.73 7	77.87 124	81.64 283	87.25 278	82.43 98	94.53 84	77.65 148	96.46 102	94.14 102

test1111		78.53 247	78.85 241	77.56 290	92.22 103	47.49 388	82.61 219	69.24 383	72.43 197	85.28 207	94.20 85	51.91 340	90.07 231	65.36 280	96.45 103	95.11 65

test9_res														80.83 108	96.45 103	90.57 242

Anonymous20240529		86.20 104	87.13 92	83.42 185	90.19 162	64.55 240	84.55 168	90.71 155	85.85 36	89.94 103	95.24 46	82.13 108	90.40 218	69.19 244	96.40 105	95.31 57

anonymousdsp		89.73 53	88.88 70	92.27 8	89.82 171	86.67 18	90.51 54	90.20 177	69.87 230	95.06 15	96.14 25	84.28 77	93.07 141	87.68 19	96.34 106	97.09 19

PHI-MVS		86.38 100	85.81 118	88.08 84	88.44 204	77.34 105	89.35 85	93.05 83	73.15 188	84.76 219	87.70 268	78.87 143	94.18 95	80.67 111	96.29 107	92.73 162

PS-MVSNAJss		88.31 73	87.90 81	89.56 59	93.31 73	77.96 96	87.94 105	91.97 119	70.73 220	94.19 25	96.67 14	76.94 167	94.57 81	83.07 81	96.28 108	96.15 33

v10		86.54 98	87.10 93	84.84 140	88.16 210	63.28 253	86.64 130	92.20 112	75.42 155	92.81 53	94.50 68	74.05 199	94.06 101	83.88 74	96.28 108	97.17 18

CNVR-MVS		87.81 83	87.68 83	88.21 83	92.87 84	77.30 107	85.25 156	91.23 142	77.31 131	87.07 169	91.47 182	82.94 91	94.71 75	84.67 67	96.27 110	92.62 169

EC-MVSNet		88.01 78	88.32 77	87.09 95	89.28 180	72.03 161	90.31 59	96.31 4	80.88 84	85.12 210	89.67 236	84.47 75	95.46 50	82.56 90	96.26 111	93.77 121

mmtdpeth		85.13 124	85.78 120	83.17 193	84.65 287	74.71 127	85.87 143	90.35 168	77.94 121	83.82 241	96.96 12	77.75 152	80.03 353	78.44 133	96.21 112	94.79 76

MM		87.64 85	87.15 91	89.09 67	89.51 174	76.39 118	88.68 96	86.76 237	84.54 46	83.58 247	93.78 108	73.36 211	96.48 2	87.98 14	96.21 112	94.41 90

114514_t		83.10 176	82.54 184	84.77 144	92.90 83	69.10 197	86.65 129	90.62 159	54.66 363	81.46 285	90.81 207	76.98 166	94.38 87	72.62 213	96.18 114	90.82 234

agg_prior2														79.68 121	96.16 115	90.22 250

AllTest		87.97 80	87.40 89	89.68 55	91.59 124	83.40 52	89.50 80	95.44 10	79.47 99	88.00 149	93.03 129	82.66 94	91.47 182	70.81 223	96.14 116	94.16 100

TestCases				89.68 55	91.59 124	83.40 52		95.44 10	79.47 99	88.00 149	93.03 129	82.66 94	91.47 182	70.81 223	96.14 116	94.16 100

EPNet		80.37 223	78.41 249	86.23 113	76.75 377	73.28 139	87.18 116	77.45 323	76.24 138	68.14 388	88.93 248	65.41 264	93.85 107	69.47 239	96.12 118	91.55 217
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testf1		89.30 60	89.12 64	89.84 52	88.67 195	85.64 35	90.61 50	93.17 76	86.02 34	93.12 44	95.30 42	84.94 69	89.44 246	74.12 189	96.10 119	94.45 86

APD_test2		89.30 60	89.12 64	89.84 52	88.67 195	85.64 35	90.61 50	93.17 76	86.02 34	93.12 44	95.30 42	84.94 69	89.44 246	74.12 189	96.10 119	94.45 86

pm-mvs1		83.69 161	84.95 135	79.91 253	90.04 168	59.66 301	82.43 227	87.44 220	75.52 153	87.85 152	95.26 45	81.25 122	85.65 310	68.74 251	96.04 121	94.42 89

test2506		74.12 295	73.39 295	76.28 308	91.85 117	44.20 402	84.06 178	48.20 423	72.30 203	81.90 274	94.20 85	27.22 423	89.77 239	64.81 285	96.02 122	94.87 70

ECVR-MVS		78.44 248	78.63 245	77.88 286	91.85 117	48.95 382	83.68 191	69.91 379	72.30 203	84.26 235	94.20 85	51.89 341	89.82 236	63.58 295	96.02 122	94.87 70

mvs_tets		89.78 52	89.27 63	91.30 29	93.51 67	84.79 44	89.89 68	90.63 158	70.00 229	94.55 19	96.67 14	87.94 39	93.59 120	84.27 71	95.97 124	95.52 51

EGC-MVSNET		74.79 290	69.99 332	89.19 65	94.89 38	87.00 15	91.89 37	86.28 241	1.09 425	2.23 427	95.98 27	81.87 115	89.48 242	79.76 119	95.96 125	91.10 225

MVS_0304		85.37 118	84.58 143	87.75 88	85.28 276	73.36 136	86.54 133	85.71 252	77.56 129	81.78 281	92.47 151	70.29 239	96.02 11	85.59 56	95.96 125	93.87 113

DeepPCF-MVS	81.24 5	87.28 88	86.21 109	90.49 42	91.48 133	84.90 42	83.41 197	92.38 107	70.25 226	89.35 119	90.68 211	82.85 92	94.57 81	79.55 123	95.95 127	92.00 201

DVP-MVS++		90.07 42	91.09 36	87.00 97	91.55 129	72.64 147	96.19 2	94.10 39	85.33 38	93.49 39	94.64 64	81.12 123	95.88 18	87.41 26	95.94 128	92.48 175

PC_three_1452									58.96 334	90.06 97	91.33 185	80.66 129	93.03 143	75.78 172	95.94 128	92.48 175

jajsoiax		89.41 57	88.81 73	91.19 32	93.38 71	84.72 45	89.70 71	90.29 174	69.27 233	94.39 20	96.38 18	86.02 65	93.52 124	83.96 73	95.92 130	95.34 55

ANet_high		83.17 174	85.68 122	75.65 313	81.24 336	45.26 399	79.94 264	92.91 91	83.83 51	91.33 76	96.88 13	80.25 133	85.92 303	68.89 248	95.89 131	95.76 43

tt0805		88.09 77	89.79 55	82.98 197	93.26 75	63.94 246	91.10 45	89.64 190	85.07 41	90.91 86	91.09 193	89.16 24	91.87 175	82.03 96	95.87 132	93.13 148

3Dnovator+	83.92 2	89.97 49	89.66 57	90.92 35	91.27 138	81.66 66	91.25 42	94.13 37	88.89 15	88.83 126	94.26 82	77.55 157	95.86 23	84.88 64	95.87 132	95.24 60

HQP_MVS		87.75 84	87.43 88	88.70 75	93.45 68	76.42 116	89.45 82	93.61 59	79.44 101	86.55 180	92.95 134	74.84 188	95.22 59	80.78 109	95.83 134	94.46 84

plane_prior5								93.61 59					95.22 59	80.78 109	95.83 134	94.46 84

cl____		80.42 221	80.23 223	81.02 238	79.99 350	59.25 305	77.07 309	87.02 233	67.37 257	86.18 191	89.21 243	63.08 279	90.16 224	76.31 166	95.80 136	93.65 126

DIV-MVS_self_test		80.43 220	80.23 223	81.02 238	79.99 350	59.25 305	77.07 309	87.02 233	67.38 256	86.19 189	89.22 242	63.09 278	90.16 224	76.32 165	95.80 136	93.66 124

DeepC-MVS_fast	80.27 8	86.23 102	85.65 123	87.96 87	91.30 136	76.92 110	87.19 115	91.99 118	70.56 221	84.96 214	90.69 210	80.01 136	95.14 64	78.37 135	95.78 138	91.82 206
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LFMVS		80.15 231	80.56 217	78.89 265	89.19 183	55.93 335	85.22 157	73.78 352	82.96 63	84.28 233	92.72 144	57.38 314	90.07 231	63.80 294	95.75 139	90.68 239

ACMMP++_ref															95.74 140

原ACMM1				84.60 149	92.81 89	74.01 132		91.50 132	62.59 296	82.73 263	90.67 213	76.53 174	94.25 91	69.24 241	95.69 141	85.55 319

tfpnnormal		81.79 202	82.95 175	78.31 276	88.93 189	55.40 341	80.83 255	82.85 289	76.81 134	85.90 197	94.14 89	74.58 194	86.51 291	66.82 265	95.68 142	93.01 154

mvs5depth		83.82 158	84.54 145	81.68 226	82.23 324	68.65 200	86.89 121	89.90 184	80.02 94	87.74 155	97.86 2	64.19 270	82.02 338	76.37 164	95.63 143	94.35 92

TAPA-MVS	77.73 12	85.71 113	84.83 136	88.37 80	88.78 194	79.72 77	87.15 117	93.50 62	69.17 234	85.80 198	89.56 237	80.76 127	92.13 166	73.21 210	95.51 144	93.25 144
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
LS3D		90.60 34	90.34 51	91.38 28	89.03 185	84.23 49	93.58 6	94.68 17	90.65 8	90.33 94	93.95 101	84.50 74	95.37 54	80.87 107	95.50 145	94.53 83

v8		86.22 103	86.83 100	84.36 156	87.82 217	62.35 269	86.42 134	91.33 139	76.78 135	92.73 55	94.48 70	73.41 208	93.72 112	83.10 80	95.41 146	97.01 21

Vis-MVSNet (Re-imp)		77.82 253	77.79 254	77.92 285	88.82 191	51.29 373	83.28 200	71.97 367	74.04 167	82.23 269	89.78 234	57.38 314	89.41 248	57.22 336	95.41 146	93.05 152

OPU-MVS				88.27 82	91.89 115	77.83 97	90.47 55				91.22 188	81.12 123	94.68 76	74.48 184	95.35 148	92.29 187

FMVSNet1		84.55 137	85.45 126	81.85 221	90.27 161	61.05 285	86.83 124	88.27 211	78.57 115	89.66 110	95.64 34	75.43 181	90.68 211	69.09 245	95.33 149	93.82 116

test12				86.57 105	90.74 151	72.63 149		90.69 156		82.76 262		79.20 140	94.80 73		95.32 150	92.27 189

NCCC		87.36 87	86.87 99	88.83 70	92.32 100	78.84 86	86.58 131	91.09 146	78.77 112	84.85 218	90.89 202	80.85 126	95.29 56	81.14 104	95.32 150	92.34 184

Patchmtry		76.56 270	77.46 255	73.83 325	79.37 359	46.60 392	82.41 228	76.90 329	73.81 170	85.56 203	92.38 153	48.07 356	83.98 327	63.36 298	95.31 152	90.92 230

XVG-OURS		89.18 63	88.83 72	90.23 47	94.28 47	86.11 26	85.91 141	93.60 61	80.16 91	89.13 123	93.44 118	83.82 80	90.98 198	83.86 75	95.30 153	93.60 130

TSAR-MVS + GP.		83.95 155	82.69 180	87.72 89	89.27 181	81.45 67	83.72 190	81.58 301	74.73 161	85.66 199	86.06 297	72.56 221	92.69 152	75.44 177	95.21 154	89.01 278

test_0402		88.65 69	89.58 60	85.88 124	92.55 92	72.22 159	84.01 179	89.44 195	88.63 20	94.38 21	95.77 29	86.38 61	93.59 120	79.84 118	95.21 154	91.82 206

TinyColmap		81.25 208	82.34 187	77.99 284	85.33 275	60.68 292	82.32 230	88.33 209	71.26 214	86.97 171	92.22 163	77.10 164	86.98 282	62.37 303	95.17 156	86.31 311

Anonymous202405211		80.51 219	81.19 210	78.49 273	88.48 202	57.26 327	76.63 316	82.49 292	81.21 80	84.30 232	92.24 162	67.99 251	86.24 295	62.22 304	95.13 157	91.98 203

tttt0517		81.07 210	79.58 233	85.52 131	88.99 187	66.45 223	87.03 119	75.51 340	73.76 171	88.32 141	90.20 224	37.96 401	94.16 99	79.36 127	95.13 157	95.93 42

DP-MVS Recon		84.05 152	83.22 168	86.52 107	91.73 122	75.27 125	83.23 204	92.40 105	72.04 206	82.04 272	88.33 256	77.91 151	93.95 104	66.17 270	95.12 159	90.34 249

PCF-MVS	74.62 15	82.15 193	80.92 213	85.84 125	89.43 177	72.30 157	80.53 257	91.82 125	57.36 347	87.81 153	89.92 232	77.67 155	93.63 115	58.69 327	95.08 160	91.58 216
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CSCG		86.26 101	86.47 104	85.60 130	90.87 149	74.26 131	87.98 104	91.85 123	80.35 88	89.54 117	88.01 260	79.09 141	92.13 166	75.51 175	95.06 161	90.41 247

SDMVSNet		81.90 201	83.17 171	78.10 281	88.81 192	62.45 266	76.08 327	86.05 247	73.67 172	83.41 250	93.04 127	82.35 100	80.65 347	70.06 235	95.03 162	91.21 222

sd_testset		79.95 235	81.39 205	75.64 314	88.81 192	58.07 319	76.16 326	82.81 290	73.67 172	83.41 250	93.04 127	80.96 125	77.65 363	58.62 328	95.03 162	91.21 222

plane_prior						76.42 116	87.15 117		75.94 145						95.03 162

new-patchmatchnet		70.10 331	73.37 296	60.29 395	81.23 337	16.95 430	59.54 406	74.62 343	62.93 294	80.97 289	87.93 263	62.83 282	71.90 379	55.24 350	95.01 165	92.00 201

v1192		84.57 136	84.69 141	84.21 162	87.75 219	62.88 257	83.02 209	91.43 134	69.08 236	89.98 102	90.89 202	72.70 219	93.62 118	82.41 92	94.97 166	96.13 34

v1921920		84.23 147	84.37 151	83.79 171	87.64 224	61.71 276	82.91 213	91.20 143	67.94 252	90.06 97	90.34 220	72.04 228	93.59 120	82.32 93	94.91 167	96.07 36

CL-MVSNet_self_test		76.81 265	77.38 257	75.12 317	86.90 243	51.34 371	73.20 355	80.63 308	68.30 246	81.80 279	88.40 255	66.92 256	80.90 344	55.35 349	94.90 168	93.12 150

CS-MVS		88.14 75	87.67 84	89.54 60	89.56 173	79.18 82	90.47 55	94.77 16	79.37 103	84.32 229	89.33 241	83.87 79	94.53 84	82.45 91	94.89 169	94.90 68

v144192		84.24 146	84.41 149	83.71 175	87.59 225	61.57 277	82.95 212	91.03 147	67.82 255	89.80 105	90.49 217	73.28 212	93.51 125	81.88 101	94.89 169	96.04 38

LCM-MVSNet-Re		83.48 168	85.06 132	78.75 268	85.94 267	55.75 339	80.05 262	94.27 24	76.47 136	96.09 6	94.54 67	83.31 88	89.75 241	59.95 322	94.89 169	90.75 235

casdiffmvs_mvg		86.72 95	87.51 86	84.36 156	87.09 238	65.22 233	84.16 175	94.23 27	77.89 122	91.28 79	93.66 114	84.35 76	92.71 150	80.07 114	94.87 172	95.16 64
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
APD_test1		88.40 71	87.91 80	89.88 51	89.50 175	86.65 20	89.98 65	91.91 122	84.26 47	90.87 89	93.92 103	82.18 107	89.29 250	73.75 197	94.81 173	93.70 123

v1240		84.30 143	84.51 147	83.65 176	87.65 223	61.26 282	82.85 215	91.54 131	67.94 252	90.68 91	90.65 214	71.71 232	93.64 114	82.84 86	94.78 174	96.07 36

MSLP-MVS++		85.00 129	86.03 112	81.90 219	91.84 119	71.56 170	86.75 128	93.02 87	75.95 144	87.12 164	89.39 239	77.98 149	89.40 249	77.46 151	94.78 174	84.75 328

IterMVS-LS		84.73 133	84.98 134	83.96 167	87.35 229	63.66 247	83.25 202	89.88 185	76.06 139	89.62 111	92.37 156	73.40 210	92.52 155	78.16 141	94.77 176	95.69 46
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AdaColmap		83.66 162	83.69 161	83.57 181	90.05 167	72.26 158	86.29 136	90.00 182	78.19 119	81.65 282	87.16 280	83.40 87	94.24 92	61.69 311	94.76 177	84.21 338

BP-MVS1		82.81 178	81.67 195	86.23 113	87.88 216	68.53 201	86.06 140	84.36 276	75.65 149	85.14 209	90.19 225	45.84 369	94.42 86	85.18 60	94.72 178	95.75 44

ITE_SJBPF				90.11 49	90.72 152	84.97 41		90.30 172	81.56 76	90.02 99	91.20 190	82.40 99	90.81 207	73.58 200	94.66 179	94.56 80

v1144		84.54 138	84.72 139	84.00 165	87.67 222	62.55 264	82.97 211	90.93 151	70.32 225	89.80 105	90.99 196	73.50 205	93.48 126	81.69 102	94.65 180	95.97 39

test20.03		73.75 299	74.59 284	71.22 346	81.11 338	51.12 375	70.15 376	72.10 366	70.42 222	80.28 303	91.50 181	64.21 269	74.72 375	46.96 394	94.58 181	87.82 296

TSAR-MVS + MP.		88.14 75	87.82 82	89.09 67	95.72 22	76.74 112	92.49 25	91.19 144	67.85 254	86.63 179	94.84 55	79.58 139	95.96 15	87.62 20	94.50 182	94.56 80
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HQP3-MVS								92.68 98							94.47 183

HQP-MVS		84.61 135	84.06 155	86.27 112	91.19 139	70.66 175	84.77 161	92.68 98	73.30 183	80.55 297	90.17 228	72.10 225	94.61 79	77.30 155	94.47 183	93.56 133

test_fmvsmconf0.01_n		86.68 96	86.52 103	87.18 94	85.94 267	78.30 89	86.93 120	92.20 112	65.94 268	89.16 121	93.16 124	83.10 89	89.89 235	87.81 16	94.43 185	93.35 137

c3_l		81.64 203	81.59 199	81.79 225	80.86 342	59.15 308	78.61 287	90.18 178	68.36 244	87.20 162	87.11 282	69.39 243	91.62 179	78.16 141	94.43 185	94.60 79

MCST-MVS		84.36 140	83.93 158	85.63 129	91.59 124	71.58 168	83.52 194	92.13 114	61.82 305	83.96 239	89.75 235	79.93 138	93.46 127	78.33 137	94.34 187	91.87 205

test_fmvsmconf0.1_n		86.18 106	85.88 116	87.08 96	85.26 277	78.25 90	85.82 145	91.82 125	65.33 282	88.55 132	92.35 158	82.62 96	89.80 237	86.87 36	94.32 188	93.18 147

thisisatest0530		79.07 238	77.33 258	84.26 161	87.13 234	64.58 238	83.66 192	75.95 335	68.86 239	85.22 208	87.36 276	38.10 398	93.57 123	75.47 176	94.28 189	94.62 78

baseline		85.20 122	85.93 114	83.02 195	86.30 256	62.37 268	84.55 168	93.96 44	74.48 164	87.12 164	92.03 164	82.30 103	91.94 171	78.39 134	94.21 190	94.74 77

test_fmvsmconf_n		85.88 111	85.51 125	86.99 98	84.77 285	78.21 91	85.40 154	91.39 137	65.32 283	87.72 156	91.81 173	82.33 101	89.78 238	86.68 38	94.20 191	92.99 155

h-mvs33		84.25 145	82.76 178	88.72 73	91.82 121	82.60 60	84.00 180	84.98 268	71.27 212	86.70 176	90.55 216	63.04 280	93.92 105	78.26 139	94.20 191	89.63 262

MVSMamba_PlusPlus		87.53 86	88.86 71	83.54 183	92.03 110	62.26 271	91.49 40	92.62 100	88.07 24	88.07 146	96.17 23	72.24 224	95.79 31	84.85 65	94.16 193	92.58 170

balanced_conf03		84.80 131	85.40 127	83.00 196	88.95 188	61.44 278	90.42 58	92.37 108	71.48 211	88.72 129	93.13 125	70.16 241	95.15 63	79.26 128	94.11 194	92.41 179

alignmvs		83.94 156	83.98 157	83.80 170	87.80 218	67.88 209	84.54 170	91.42 136	73.27 186	88.41 138	87.96 261	72.33 222	90.83 206	76.02 171	94.11 194	92.69 166

USDC		76.63 268	76.73 265	76.34 307	83.46 308	57.20 328	80.02 263	88.04 215	52.14 378	83.65 245	91.25 187	63.24 276	86.65 289	54.66 354	94.11 194	85.17 323

MVS_111021_HR		84.63 134	84.34 152	85.49 133	90.18 163	75.86 123	79.23 278	87.13 228	73.35 180	85.56 203	89.34 240	83.60 85	90.50 216	76.64 161	94.05 197	90.09 256

VNet		79.31 237	80.27 222	76.44 305	87.92 215	53.95 352	75.58 333	84.35 277	74.39 165	82.23 269	90.72 209	72.84 217	84.39 322	60.38 320	93.98 198	90.97 228

FMVSNet2		81.31 207	81.61 198	80.41 247	86.38 251	58.75 315	83.93 183	86.58 239	72.43 197	87.65 157	92.98 131	63.78 273	90.22 222	66.86 262	93.92 199	92.27 189

MGCFI-Net		85.04 126	85.95 113	82.31 215	87.52 226	63.59 249	86.23 138	93.96 44	73.46 176	88.07 146	87.83 266	86.46 57	90.87 205	76.17 168	93.89 200	92.47 177

GDP-MVS		82.17 191	80.85 215	86.15 120	88.65 197	68.95 198	85.65 149	93.02 87	68.42 243	83.73 243	89.54 238	45.07 380	94.31 88	79.66 122	93.87 201	95.19 63

LF4IMVS		82.75 180	81.93 191	85.19 135	82.08 325	80.15 74	85.53 150	88.76 202	68.01 249	85.58 202	87.75 267	71.80 230	86.85 285	74.02 192	93.87 201	88.58 281

sasdasda		85.50 114	86.14 110	83.58 179	87.97 212	67.13 213	87.55 109	94.32 21	73.44 178	88.47 135	87.54 271	86.45 58	91.06 196	75.76 173	93.76 203	92.54 173

canonicalmvs		85.50 114	86.14 110	83.58 179	87.97 212	67.13 213	87.55 109	94.32 21	73.44 178	88.47 135	87.54 271	86.45 58	91.06 196	75.76 173	93.76 203	92.54 173

v2v482		84.09 150	84.24 153	83.62 177	87.13 234	61.40 279	82.71 218	89.71 188	72.19 205	89.55 115	91.41 183	70.70 238	93.20 135	81.02 105	93.76 203	96.25 32

casdiffmvs		85.21 121	85.85 117	83.31 188	86.17 261	62.77 260	83.03 208	93.93 46	74.69 162	88.21 143	92.68 145	82.29 104	91.89 174	77.87 147	93.75 206	95.27 59
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UGNet		82.78 179	81.64 196	86.21 116	86.20 260	76.24 120	86.86 122	85.68 253	77.07 133	73.76 360	92.82 139	69.64 242	91.82 177	69.04 247	93.69 207	90.56 243
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
旧先验1					91.97 111	71.77 163		81.78 298			91.84 170	73.92 200			93.65 208	83.61 346

AUN-MVS		81.18 209	78.78 242	88.39 79	90.93 147	82.14 62	82.51 225	83.67 282	64.69 287	80.29 301	85.91 301	51.07 344	92.38 159	76.29 167	93.63 209	90.65 241

hse-mvs2		83.47 169	81.81 193	88.47 77	91.03 145	82.27 61	82.61 219	83.69 281	71.27 212	86.70 176	86.05 298	63.04 280	92.41 158	78.26 139	93.62 210	90.71 237

MVS_111021_LR		84.28 144	83.76 160	85.83 126	89.23 182	83.07 55	80.99 251	83.56 283	72.71 195	86.07 192	89.07 246	81.75 117	86.19 298	77.11 157	93.36 211	88.24 284

GBi-Net		82.02 196	82.07 188	81.85 221	86.38 251	61.05 285	86.83 124	88.27 211	72.43 197	86.00 193	95.64 34	63.78 273	90.68 211	65.95 272	93.34 212	93.82 116

test1		82.02 196	82.07 188	81.85 221	86.38 251	61.05 285	86.83 124	88.27 211	72.43 197	86.00 193	95.64 34	63.78 273	90.68 211	65.95 272	93.34 212	93.82 116

FMVSNet3		78.80 243	78.55 246	79.57 259	82.89 322	56.89 331	81.76 239	85.77 251	69.04 237	86.00 193	90.44 218	51.75 342	90.09 230	65.95 272	93.34 212	91.72 210

test_fmvsmvis_n_1920		85.22 120	85.36 129	84.81 142	85.80 269	76.13 122	85.15 159	92.32 109	61.40 312	91.33 76	90.85 205	83.76 83	86.16 299	84.31 70	93.28 215	92.15 195

K. test v3		85.14 123	84.73 137	86.37 109	91.13 143	69.63 188	85.45 152	76.68 332	84.06 50	92.44 60	96.99 10	62.03 283	94.65 77	80.58 112	93.24 216	94.83 75

Anonymous20231206		71.38 321	71.88 312	69.88 353	86.31 255	54.37 348	70.39 374	74.62 343	52.57 374	76.73 332	88.76 249	59.94 295	72.06 378	44.35 401	93.23 217	83.23 354

D2MVS		76.84 264	75.67 275	80.34 248	80.48 348	62.16 274	73.50 352	84.80 273	57.61 345	82.24 268	87.54 271	51.31 343	87.65 272	70.40 232	93.19 218	91.23 221

miper_lstm_enhance		76.45 272	76.10 270	77.51 291	76.72 378	60.97 289	64.69 396	85.04 265	63.98 290	83.20 254	88.22 257	56.67 318	78.79 360	73.22 205	93.12 219	92.78 161

新几何1				82.95 199	93.96 59	78.56 88		80.24 309	55.45 357	83.93 240	91.08 194	71.19 235	88.33 264	65.84 275	93.07 220	81.95 370

lessismore_v0				85.95 121	91.10 144	70.99 174		70.91 375		91.79 69	94.42 74	61.76 284	92.93 146	79.52 125	93.03 221	93.93 109

TAMVS		78.08 251	76.36 267	83.23 190	90.62 154	72.87 143	79.08 279	80.01 311	61.72 308	81.35 287	86.92 285	63.96 272	88.78 258	50.61 375	93.01 222	88.04 290

ETV-MVS		84.31 142	83.91 159	85.52 131	88.58 200	70.40 178	84.50 172	93.37 64	78.76 113	84.07 237	78.72 379	80.39 131	95.13 65	73.82 196	92.98 223	91.04 226

EPNet_dtu		72.87 307	71.33 319	77.49 292	77.72 368	60.55 293	82.35 229	75.79 336	66.49 267	58.39 418	81.06 358	53.68 333	85.98 301	53.55 360	92.97 224	85.95 314
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Effi-MVS+-dtu		85.82 112	83.38 165	93.14 4	87.13 234	91.15 3	87.70 108	88.42 206	74.57 163	83.56 248	85.65 302	78.49 146	94.21 93	72.04 217	92.88 225	94.05 105

CANet		83.79 160	82.85 177	86.63 104	86.17 261	72.21 160	83.76 189	91.43 134	77.24 132	74.39 356	87.45 274	75.36 182	95.42 52	77.03 158	92.83 226	92.25 191

fmvsm_s_conf0.5_n_3		86.19 105	87.27 90	82.95 199	86.91 242	70.38 179	85.31 155	92.61 101	75.59 151	88.32 141	92.87 137	82.22 106	88.63 261	88.80 8	92.82 227	89.83 260

API-MVS		82.28 187	82.61 182	81.30 231	86.29 257	69.79 184	88.71 95	87.67 218	78.42 117	82.15 271	84.15 327	77.98 149	91.59 180	65.39 279	92.75 228	82.51 365

test_yl		78.71 245	78.51 247	79.32 262	84.32 294	58.84 312	78.38 288	85.33 258	75.99 142	82.49 264	86.57 288	58.01 308	90.02 233	62.74 301	92.73 229	89.10 273

DCV-MVSNet		78.71 245	78.51 247	79.32 262	84.32 294	58.84 312	78.38 288	85.33 258	75.99 142	82.49 264	86.57 288	58.01 308	90.02 233	62.74 301	92.73 229	89.10 273

testgi		72.36 310	74.61 282	65.59 379	80.56 347	42.82 407	68.29 382	73.35 356	66.87 264	81.84 276	89.93 231	72.08 227	66.92 401	46.05 397	92.54 231	87.01 304

FMVSNet5		72.10 313	71.69 313	73.32 328	81.57 332	53.02 359	76.77 313	78.37 318	63.31 291	76.37 334	91.85 169	36.68 403	78.98 357	47.87 390	92.45 232	87.95 292

CDS-MVSNet		77.32 259	75.40 276	83.06 194	89.00 186	72.48 154	77.90 295	82.17 295	60.81 321	78.94 316	83.49 332	59.30 300	88.76 259	54.64 355	92.37 233	87.93 293
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
patch_mono-2		78.89 240	79.39 235	77.41 293	84.78 284	68.11 206	75.60 331	83.11 286	60.96 320	79.36 311	89.89 233	75.18 184	72.97 376	73.32 204	92.30 234	91.15 224

dcpmvs_2		84.23 147	85.14 131	81.50 229	88.61 199	61.98 275	82.90 214	93.11 79	68.66 242	92.77 54	92.39 152	78.50 145	87.63 273	76.99 159	92.30 234	94.90 68

CNLPA		83.55 167	83.10 173	84.90 139	89.34 179	83.87 50	84.54 170	88.77 201	79.09 106	83.54 249	88.66 253	74.87 187	81.73 340	66.84 264	92.29 236	89.11 272

F-COLMAP		84.97 130	83.42 164	89.63 57	92.39 96	83.40 52	88.83 92	91.92 121	73.19 187	80.18 305	89.15 245	77.04 165	93.28 133	65.82 276	92.28 237	92.21 192

thres600view7		75.97 276	75.35 278	77.85 288	87.01 240	51.84 369	80.45 258	73.26 357	75.20 157	83.10 256	86.31 294	45.54 371	89.05 251	55.03 352	92.24 238	92.66 167

PVSNet_BlendedMVS		78.80 243	77.84 253	81.65 227	84.43 290	63.41 250	79.49 272	90.44 163	61.70 309	75.43 347	87.07 283	69.11 246	91.44 184	60.68 318	92.24 238	90.11 255

DELS-MVS		81.44 206	81.25 207	82.03 217	84.27 296	62.87 258	76.47 321	92.49 104	70.97 218	81.64 283	83.83 328	75.03 185	92.70 151	74.29 185	92.22 240	90.51 245
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
testdata				79.54 260	92.87 84	72.34 156		80.14 310	59.91 330	85.47 205	91.75 176	67.96 252	85.24 312	68.57 255	92.18 241	81.06 383

SSC-MVS		77.55 256	81.64 196	65.29 382	90.46 157	20.33 428	73.56 351	68.28 385	85.44 37	88.18 145	94.64 64	70.93 236	81.33 342	71.25 220	92.03 242	94.20 96

cl22		78.97 239	78.21 251	81.24 234	77.74 367	59.01 309	77.46 305	87.13 228	65.79 272	84.32 229	85.10 313	58.96 304	90.88 204	75.36 178	92.03 242	93.84 114

miper_ehance_all_eth		80.34 224	80.04 230	81.24 234	79.82 353	58.95 310	77.66 298	89.66 189	65.75 275	85.99 196	85.11 312	68.29 250	91.42 186	76.03 170	92.03 242	93.33 138

miper_enhance_ethall		77.83 252	76.93 262	80.51 245	76.15 384	58.01 321	75.47 335	88.82 200	58.05 341	83.59 246	80.69 359	64.41 267	91.20 190	73.16 211	92.03 242	92.33 185

GeoE		85.45 117	85.81 118	84.37 154	90.08 164	67.07 215	85.86 144	91.39 137	72.33 202	87.59 158	90.25 223	84.85 71	92.37 160	78.00 144	91.94 246	93.66 124

fmvsm_s_conf0.1_n_2		83.82 158	83.49 162	84.84 140	85.99 266	70.19 182	80.93 252	87.58 219	67.26 260	87.94 151	92.37 156	71.40 234	88.01 267	86.03 50	91.87 247	96.31 31

DPM-MVS		80.10 232	79.18 237	82.88 204	90.71 153	69.74 185	78.87 283	90.84 152	60.29 327	75.64 346	85.92 300	67.28 253	93.11 139	71.24 221	91.79 248	85.77 317

v148		82.31 186	82.48 185	81.81 224	85.59 271	59.66 301	81.47 244	86.02 248	72.85 191	88.05 148	90.65 214	70.73 237	90.91 202	75.15 180	91.79 248	94.87 70

fmvsm_s_conf0.5_n_2		83.62 164	83.29 167	84.62 148	85.43 274	70.18 183	80.61 256	87.24 224	67.14 261	87.79 154	91.87 167	71.79 231	87.98 268	86.00 54	91.77 250	95.71 45

test222					93.31 73	76.54 113	79.38 273	77.79 320	52.59 373	82.36 267	90.84 206	66.83 257			91.69 251	81.25 378

testing3		71.53 319	70.79 320	73.77 326	88.89 190	41.86 409	76.60 319	59.12 413	72.83 192	80.97 289	82.08 349	19.80 429	87.33 277	65.12 282	91.68 252	92.13 196

eth_miper_zixun_eth		80.84 213	80.22 225	82.71 206	81.41 334	60.98 288	77.81 296	90.14 179	67.31 259	86.95 172	87.24 279	64.26 268	92.31 162	75.23 179	91.61 253	94.85 74

pmmvs-eth3d		78.42 249	77.04 261	82.57 211	87.44 228	74.41 130	80.86 254	79.67 312	55.68 356	84.69 220	90.31 222	60.91 288	85.42 311	62.20 305	91.59 254	87.88 294

Vis-MVSNet		86.86 92	86.58 102	87.72 89	92.09 107	77.43 104	87.35 113	92.09 115	78.87 110	84.27 234	94.05 92	78.35 147	93.65 113	80.54 113	91.58 255	92.08 197
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
FE-MVS		79.98 234	78.86 240	83.36 186	86.47 248	66.45 223	89.73 70	84.74 274	72.80 193	84.22 236	91.38 184	44.95 381	93.60 119	63.93 292	91.50 256	90.04 257

thisisatest0515		73.00 306	70.52 324	80.46 246	81.45 333	59.90 299	73.16 356	74.31 347	57.86 342	76.08 341	77.78 384	37.60 402	92.12 168	65.00 283	91.45 257	89.35 267

ppachtmachnet_test		74.73 291	74.00 289	76.90 299	80.71 345	56.89 331	71.53 366	78.42 317	58.24 338	79.32 313	82.92 340	57.91 311	84.26 324	65.60 278	91.36 258	89.56 263

FA-MVS(test-final)		83.13 175	83.02 174	83.43 184	86.16 263	66.08 226	88.00 103	88.36 208	75.55 152	85.02 212	92.75 143	65.12 265	92.50 156	74.94 183	91.30 259	91.72 210

OpenMVS	76.72 13	81.98 198	82.00 190	81.93 218	84.42 292	68.22 204	88.50 99	89.48 194	66.92 263	81.80 279	91.86 168	72.59 220	90.16 224	71.19 222	91.25 260	87.40 300

EG-PatchMatch MVS		84.08 151	84.11 154	83.98 166	92.22 103	72.61 150	82.20 237	87.02 233	72.63 196	88.86 124	91.02 195	78.52 144	91.11 194	73.41 202	91.09 261	88.21 285

3Dnovator	80.37 7	84.80 131	84.71 140	85.06 138	86.36 254	74.71 127	88.77 94	90.00 182	75.65 149	84.96 214	93.17 123	74.06 198	91.19 191	78.28 138	91.09 261	89.29 270

thres100view900		75.45 280	75.05 280	76.66 303	87.27 230	51.88 368	81.07 250	73.26 357	75.68 148	83.25 253	86.37 291	45.54 371	88.80 255	51.98 370	90.99 263	89.31 268

tfpn200view9		74.86 288	74.23 287	76.74 302	86.24 258	52.12 365	79.24 276	73.87 350	73.34 181	81.82 277	84.60 322	46.02 364	88.80 255	51.98 370	90.99 263	89.31 268

thres400		75.14 282	74.23 287	77.86 287	86.24 258	52.12 365	79.24 276	73.87 350	73.34 181	81.82 277	84.60 322	46.02 364	88.80 255	51.98 370	90.99 263	92.66 167

cascas		76.29 274	74.81 281	80.72 243	84.47 289	62.94 256	73.89 349	87.34 221	55.94 354	75.16 352	76.53 396	63.97 271	91.16 192	65.00 283	90.97 266	88.06 289

MSP-MVS		89.08 66	88.16 78	91.83 20	95.76 18	86.14 25	92.75 17	93.90 48	78.43 116	89.16 121	92.25 161	72.03 229	96.36 4	88.21 12	90.93 267	92.98 156
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
WBMVS		68.76 346	68.43 346	69.75 355	83.29 313	40.30 412	67.36 388	72.21 365	57.09 350	77.05 331	85.53 304	33.68 408	80.51 348	48.79 385	90.90 268	88.45 283

ab-mvs		79.67 236	80.56 217	76.99 296	88.48 202	56.93 329	84.70 165	86.06 246	68.95 238	80.78 294	93.08 126	75.30 183	84.62 318	56.78 337	90.90 268	89.43 266

test_fmvsm_n_1920		83.60 165	82.89 176	85.74 127	85.22 278	77.74 99	84.12 177	90.48 161	59.87 331	86.45 188	91.12 192	75.65 179	85.89 306	82.28 94	90.87 270	93.58 131

MAR-MVS		80.24 228	78.74 244	84.73 145	86.87 245	78.18 92	85.75 146	87.81 217	65.67 277	77.84 324	78.50 380	73.79 202	90.53 215	61.59 313	90.87 270	85.49 321
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
EI-MVSNet-Vis-set		85.12 125	84.53 146	86.88 100	84.01 299	72.76 144	83.91 184	85.18 261	80.44 86	88.75 127	85.49 305	80.08 135	91.92 172	82.02 97	90.85 272	95.97 39

EI-MVSNet-UG-set		85.04 126	84.44 148	86.85 101	83.87 303	72.52 153	83.82 186	85.15 262	80.27 90	88.75 127	85.45 307	79.95 137	91.90 173	81.92 100	90.80 273	96.13 34

XVG-OURS-SEG-HR		89.59 55	89.37 61	90.28 46	94.47 43	85.95 27	86.84 123	93.91 47	80.07 93	86.75 175	93.26 121	93.64 2	90.93 200	84.60 68	90.75 274	93.97 107

ET-MVSNet_ETH3D		75.28 281	72.77 303	82.81 205	83.03 321	68.11 206	77.09 308	76.51 333	60.67 324	77.60 329	80.52 363	38.04 399	91.15 193	70.78 225	90.68 275	89.17 271

EI-MVSNet		82.61 181	82.42 186	83.20 191	83.25 315	63.66 247	83.50 195	85.07 263	76.06 139	86.55 180	85.10 313	73.41 208	90.25 219	78.15 143	90.67 276	95.68 47

MVSTER		77.09 261	75.70 274	81.25 232	75.27 392	61.08 284	77.49 304	85.07 263	60.78 322	86.55 180	88.68 251	43.14 390	90.25 219	73.69 199	90.67 276	92.42 178

reproduce_monomvs		74.09 296	73.23 297	76.65 304	76.52 379	54.54 347	77.50 303	81.40 302	65.85 271	82.86 261	86.67 287	27.38 421	84.53 319	70.24 233	90.66 278	90.89 231

Patchmatch-RL test		74.48 292	73.68 291	76.89 300	84.83 283	66.54 221	72.29 359	69.16 384	57.70 343	86.76 174	86.33 292	45.79 370	82.59 334	69.63 238	90.65 279	81.54 374

CMPMVS	59.41 20	75.12 284	73.57 292	79.77 254	75.84 387	67.22 212	81.21 248	82.18 294	50.78 387	76.50 333	87.66 269	55.20 328	82.99 333	62.17 307	90.64 280	89.09 275
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
WB-MVS		76.06 275	80.01 231	64.19 385	89.96 170	20.58 427	72.18 360	68.19 386	83.21 59	86.46 187	93.49 117	70.19 240	78.97 358	65.96 271	90.46 281	93.02 153

fmvsm_l_conf0.5_n		82.06 195	81.54 202	83.60 178	83.94 300	73.90 133	83.35 199	86.10 244	58.97 333	83.80 242	90.36 219	74.23 196	86.94 283	82.90 84	90.22 282	89.94 258

V42		83.47 169	83.37 166	83.75 173	83.16 318	63.33 252	81.31 245	90.23 176	69.51 232	90.91 86	90.81 207	74.16 197	92.29 164	80.06 115	90.22 282	95.62 49

PM-MVS		80.20 229	79.00 238	83.78 172	88.17 209	86.66 19	81.31 245	66.81 394	69.64 231	88.33 140	90.19 225	64.58 266	83.63 330	71.99 218	90.03 284	81.06 383

PLC	73.85 16	82.09 194	80.31 221	87.45 92	90.86 150	80.29 73	85.88 142	90.65 157	68.17 248	76.32 336	86.33 292	73.12 214	92.61 154	61.40 314	90.02 285	89.44 265
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
fmvsm_l_conf0.5_n_a		81.46 205	80.87 214	83.25 189	83.73 305	73.21 142	83.00 210	85.59 255	58.22 339	82.96 258	90.09 230	72.30 223	86.65 289	81.97 99	89.95 286	89.88 259

ttmdpeth		71.72 316	70.67 321	74.86 319	73.08 405	55.88 336	77.41 306	69.27 382	55.86 355	78.66 318	93.77 110	38.01 400	75.39 372	60.12 321	89.87 287	93.31 140

UWE-MVS		66.43 359	65.56 364	69.05 360	84.15 298	40.98 410	73.06 357	64.71 400	54.84 361	76.18 339	79.62 372	29.21 416	80.50 349	38.54 413	89.75 288	85.66 318

CANet_DTU		77.81 254	77.05 260	80.09 252	81.37 335	59.90 299	83.26 201	88.29 210	69.16 235	67.83 391	83.72 329	60.93 287	89.47 243	69.22 243	89.70 289	90.88 232

diffmvs		80.40 222	80.48 220	80.17 251	79.02 363	60.04 296	77.54 301	90.28 175	66.65 266	82.40 266	87.33 277	73.50 205	87.35 276	77.98 145	89.62 290	93.13 148
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVStest1		70.05 333	69.26 336	72.41 340	58.62 427	55.59 340	76.61 318	65.58 396	53.44 368	89.28 120	93.32 120	22.91 427	71.44 383	74.08 191	89.52 291	90.21 254

PMMVS2		55.64 387	59.27 386	44.74 403	64.30 425	12.32 431	40.60 418	49.79 422	53.19 370	65.06 405	84.81 318	53.60 334	49.76 421	32.68 420	89.41 292	72.15 402

Fast-Effi-MVS+-dtu		82.54 184	81.41 204	85.90 123	85.60 270	76.53 115	83.07 207	89.62 192	73.02 190	79.11 315	83.51 331	80.74 128	90.24 221	68.76 250	89.29 293	90.94 229

thres200		72.34 311	71.55 317	74.70 322	83.48 307	51.60 370	75.02 338	73.71 353	70.14 228	78.56 320	80.57 362	46.20 362	88.20 266	46.99 393	89.29 293	84.32 334

jason		77.42 258	75.75 273	82.43 214	87.10 237	69.27 191	77.99 293	81.94 297	51.47 382	77.84 324	85.07 316	60.32 292	89.00 252	70.74 227	89.27 295	89.03 276
jason: jason.
MG-MVS		80.32 225	80.94 212	78.47 274	88.18 208	52.62 363	82.29 231	85.01 267	72.01 207	79.24 314	92.54 149	69.36 244	93.36 132	70.65 228	89.19 296	89.45 264

BH-untuned		80.96 212	80.99 211	80.84 240	88.55 201	68.23 203	80.33 260	88.46 205	72.79 194	86.55 180	86.76 286	74.72 192	91.77 178	61.79 310	88.99 297	82.52 364

EIA-MVS		82.19 190	81.23 209	85.10 137	87.95 214	69.17 196	83.22 205	93.33 67	70.42 222	78.58 319	79.77 371	77.29 160	94.20 94	71.51 219	88.96 298	91.93 204

PVSNet_Blended_VisFu		81.55 204	80.49 219	84.70 147	91.58 127	73.24 141	84.21 174	91.67 129	62.86 295	80.94 291	87.16 280	67.27 254	92.87 149	69.82 237	88.94 299	87.99 291

MVSFormer		82.23 188	81.57 201	84.19 164	85.54 272	69.26 192	91.98 34	90.08 180	71.54 209	76.23 337	85.07 316	58.69 305	94.27 89	86.26 44	88.77 300	89.03 276

lupinMVS		76.37 273	74.46 285	82.09 216	85.54 272	69.26 192	76.79 312	80.77 307	50.68 389	76.23 337	82.82 341	58.69 305	88.94 253	69.85 236	88.77 300	88.07 287

RPSCF		88.00 79	86.93 98	91.22 31	90.08 164	89.30 5	89.68 73	91.11 145	79.26 104	89.68 108	94.81 59	82.44 97	87.74 271	76.54 162	88.74 302	96.61 27

test_fmvs3		75.72 279	75.20 279	77.27 294	75.01 395	69.47 189	78.93 280	84.88 270	46.67 396	87.08 168	87.84 265	50.44 349	71.62 381	77.42 154	88.53 303	90.72 236

RRT-MVS		82.97 177	83.44 163	81.57 228	85.06 280	58.04 320	87.20 114	90.37 166	77.88 123	88.59 131	93.70 113	63.17 277	93.05 142	76.49 163	88.47 304	93.62 128

PAPM_NR		83.23 172	83.19 170	83.33 187	90.90 148	65.98 227	88.19 101	90.78 154	78.13 120	80.87 293	87.92 264	73.49 207	92.42 157	70.07 234	88.40 305	91.60 215

testing222		66.93 353	65.30 365	71.81 343	83.38 310	45.83 396	72.06 361	67.50 387	64.12 289	69.68 382	76.37 397	27.34 422	83.00 332	38.88 410	88.38 306	86.62 308

xiu_mvs_v1_base_debu		80.84 213	80.14 227	82.93 201	88.31 205	71.73 164	79.53 269	87.17 225	65.43 278	79.59 307	82.73 343	76.94 167	90.14 227	73.22 205	88.33 307	86.90 305

xiu_mvs_v1_base		80.84 213	80.14 227	82.93 201	88.31 205	71.73 164	79.53 269	87.17 225	65.43 278	79.59 307	82.73 343	76.94 167	90.14 227	73.22 205	88.33 307	86.90 305

xiu_mvs_v1_base_debi		80.84 213	80.14 227	82.93 201	88.31 205	71.73 164	79.53 269	87.17 225	65.43 278	79.59 307	82.73 343	76.94 167	90.14 227	73.22 205	88.33 307	86.90 305

XXY-MVS		74.44 294	76.19 269	69.21 359	84.61 288	52.43 364	71.70 363	77.18 327	60.73 323	80.60 295	90.96 199	75.44 180	69.35 388	56.13 342	88.33 307	85.86 316

Fast-Effi-MVS+		81.04 211	80.57 216	82.46 213	87.50 227	63.22 254	78.37 290	89.63 191	68.01 249	81.87 275	82.08 349	82.31 102	92.65 153	67.10 261	88.30 311	91.51 218

MDA-MVSNet-bldmvs		77.47 257	76.90 263	79.16 264	79.03 362	64.59 237	66.58 392	75.67 338	73.15 188	88.86 124	88.99 247	66.94 255	81.23 343	64.71 286	88.22 312	91.64 214

PAPR		78.84 242	78.10 252	81.07 236	85.17 279	60.22 295	82.21 235	90.57 160	62.51 297	75.32 350	84.61 321	74.99 186	92.30 163	59.48 325	88.04 313	90.68 239

mvsmamba		80.30 226	78.87 239	84.58 150	88.12 211	67.55 211	92.35 29	84.88 270	63.15 293	85.33 206	90.91 201	50.71 346	95.20 62	66.36 268	87.98 314	90.99 227

BH-RMVSNet		80.53 218	80.22 225	81.49 230	87.19 233	66.21 225	77.79 297	86.23 242	74.21 166	83.69 244	88.50 254	73.25 213	90.75 208	63.18 300	87.90 315	87.52 298

Effi-MVS+		83.90 157	84.01 156	83.57 181	87.22 232	65.61 231	86.55 132	92.40 105	78.64 114	81.34 288	84.18 326	83.65 84	92.93 146	74.22 186	87.87 316	92.17 194

MVS_Test		82.47 185	83.22 168	80.22 250	82.62 323	57.75 324	82.54 224	91.96 120	71.16 216	82.89 259	92.52 150	77.41 158	90.50 216	80.04 116	87.84 317	92.40 181

QAPM		82.59 182	82.59 183	82.58 209	86.44 249	66.69 220	89.94 67	90.36 167	67.97 251	84.94 216	92.58 148	72.71 218	92.18 165	70.63 229	87.73 318	88.85 279

PVSNet_Blended		76.49 271	75.40 276	79.76 255	84.43 290	63.41 250	75.14 337	90.44 163	57.36 347	75.43 347	78.30 381	69.11 246	91.44 184	60.68 318	87.70 319	84.42 333

pmmvs5		70.73 326	70.07 329	72.72 334	77.03 375	52.73 361	74.14 344	75.65 339	50.36 391	72.17 368	85.37 310	55.42 327	80.67 346	52.86 366	87.59 320	84.77 327

IB-MVS	62.13 19	71.64 317	68.97 342	79.66 258	80.80 344	62.26 271	73.94 348	76.90 329	63.27 292	68.63 387	76.79 393	33.83 407	91.84 176	59.28 326	87.26 321	84.88 326
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
N_pmnet		70.20 329	68.80 344	74.38 323	80.91 340	84.81 43	59.12 408	76.45 334	55.06 359	75.31 351	82.36 346	55.74 324	54.82 418	47.02 392	87.24 322	83.52 347

fmvsm_s_conf0.1_n		82.17 191	81.59 199	83.94 169	86.87 245	71.57 169	85.19 158	77.42 324	62.27 304	84.47 225	91.33 185	76.43 175	85.91 304	83.14 78	87.14 323	94.33 94

fmvsm_s_conf0.5_n		81.91 200	81.30 206	83.75 173	86.02 265	71.56 170	84.73 164	77.11 328	62.44 301	84.00 238	90.68 211	76.42 176	85.89 306	83.14 78	87.11 324	93.81 119

fmvsm_s_conf0.1_n_a		82.58 183	81.93 191	84.50 151	87.68 221	73.35 137	86.14 139	77.70 321	61.64 310	85.02 212	91.62 178	77.75 152	86.24 295	82.79 87	87.07 325	93.91 111

pmmvs4		74.92 287	72.98 301	80.73 242	84.95 281	71.71 167	76.23 324	77.59 322	52.83 372	77.73 328	86.38 290	56.35 321	84.97 315	57.72 335	87.05 326	85.51 320

test_fmvs2		73.57 300	72.80 302	75.90 312	72.74 408	68.84 199	77.07 309	84.32 278	45.14 402	82.89 259	84.22 325	48.37 354	70.36 385	73.40 203	87.03 327	88.52 282

MIMVSNet		71.09 323	71.59 314	69.57 357	87.23 231	50.07 380	78.91 281	71.83 368	60.20 329	71.26 371	91.76 175	55.08 330	76.09 368	41.06 406	87.02 328	82.54 363

testing91		69.94 336	68.99 341	72.80 333	83.81 304	45.89 395	71.57 365	73.64 355	68.24 247	70.77 377	77.82 383	34.37 406	84.44 321	53.64 359	87.00 329	88.07 287

fmvsm_s_conf0.5_n_a		82.21 189	81.51 203	84.32 159	86.56 247	73.35 137	85.46 151	77.30 325	61.81 306	84.51 222	90.88 204	77.36 159	86.21 297	82.72 88	86.97 330	93.38 136

HyFIR lowres test		75.12 284	72.66 305	82.50 212	91.44 135	65.19 234	72.47 358	87.31 222	46.79 395	80.29 301	84.30 324	52.70 337	92.10 169	51.88 374	86.73 331	90.22 250

test_vis3_rt		71.42 320	70.67 321	73.64 327	69.66 415	70.46 177	66.97 391	89.73 186	42.68 412	88.20 144	83.04 336	43.77 385	60.07 413	65.35 281	86.66 332	90.39 248

MSDG		80.06 233	79.99 232	80.25 249	83.91 302	68.04 208	77.51 302	89.19 197	77.65 126	81.94 273	83.45 333	76.37 177	86.31 294	63.31 299	86.59 333	86.41 309

Patchmatch-test		65.91 362	67.38 351	61.48 393	75.51 389	43.21 406	68.84 380	63.79 402	62.48 298	72.80 365	83.42 334	44.89 382	59.52 415	48.27 389	86.45 334	81.70 371

mvs_anonymous		78.13 250	78.76 243	76.23 310	79.24 360	50.31 379	78.69 285	84.82 272	61.60 311	83.09 257	92.82 139	73.89 201	87.01 279	68.33 257	86.41 335	91.37 219

IterMVS-SCA-FT		80.64 217	79.41 234	84.34 158	83.93 301	69.66 187	76.28 323	81.09 304	72.43 197	86.47 186	90.19 225	60.46 290	93.15 138	77.45 152	86.39 336	90.22 250

testing99		69.27 342	68.15 349	72.63 335	83.29 313	45.45 397	71.15 367	71.08 373	67.34 258	70.43 378	77.77 385	32.24 411	84.35 323	53.72 358	86.33 337	88.10 286

E-PMN		61.59 376	61.62 379	61.49 392	66.81 419	55.40 341	53.77 415	60.34 412	66.80 265	58.90 416	65.50 415	40.48 395	66.12 404	55.72 344	86.25 338	62.95 413

EMVS		61.10 379	60.81 381	61.99 390	65.96 422	55.86 337	53.10 416	58.97 415	67.06 262	56.89 420	63.33 416	40.98 393	67.03 400	54.79 353	86.18 339	63.08 412

ETVMVS		64.67 367	63.34 373	68.64 364	83.44 309	41.89 408	69.56 379	61.70 409	61.33 315	68.74 385	75.76 399	28.76 417	79.35 354	34.65 417	86.16 340	84.67 329

our_test_3		71.85 314	71.59 314	72.62 336	80.71 345	53.78 353	69.72 378	71.71 371	58.80 335	78.03 321	80.51 364	56.61 319	78.84 359	62.20 305	86.04 341	85.23 322

EU-MVSNet		75.12 284	74.43 286	77.18 295	83.11 320	59.48 303	85.71 148	82.43 293	39.76 416	85.64 200	88.76 249	44.71 383	87.88 270	73.86 195	85.88 342	84.16 339

GA-MVS		75.83 277	74.61 282	79.48 261	81.87 327	59.25 305	73.42 353	82.88 288	68.68 241	79.75 306	81.80 352	50.62 347	89.46 244	66.85 263	85.64 343	89.72 261

MVS		73.21 304	72.59 306	75.06 318	80.97 339	60.81 291	81.64 242	85.92 250	46.03 400	71.68 370	77.54 386	68.47 249	89.77 239	55.70 345	85.39 344	74.60 400

PatchT		70.52 327	72.76 304	63.79 387	79.38 358	33.53 421	77.63 299	65.37 398	73.61 174	71.77 369	92.79 142	44.38 384	75.65 371	64.53 290	85.37 345	82.18 367

TR-MVS		76.77 266	75.79 272	79.72 256	86.10 264	65.79 229	77.14 307	83.02 287	65.20 284	81.40 286	82.10 347	66.30 258	90.73 210	55.57 346	85.27 346	82.65 359

BH-w/o		76.57 269	76.07 271	78.10 281	86.88 244	65.92 228	77.63 299	86.33 240	65.69 276	80.89 292	79.95 368	68.97 248	90.74 209	53.01 365	85.25 347	77.62 394

Syy-MVS		69.40 341	70.03 331	67.49 371	81.72 329	38.94 414	71.00 368	61.99 404	61.38 313	70.81 375	72.36 407	61.37 286	79.30 355	64.50 291	85.18 348	84.22 336

myMVS_eth3d		64.66 368	63.89 369	66.97 374	81.72 329	37.39 417	71.00 368	61.99 404	61.38 313	70.81 375	72.36 407	20.96 428	79.30 355	49.59 380	85.18 348	84.22 336

IterMVS		76.91 263	76.34 268	78.64 270	80.91 340	64.03 244	76.30 322	79.03 315	64.88 286	83.11 255	89.16 244	59.90 296	84.46 320	68.61 253	85.15 350	87.42 299
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WB-MVSnew		68.72 347	69.01 340	67.85 368	83.22 317	43.98 403	74.93 339	65.98 395	55.09 358	73.83 359	79.11 374	65.63 263	71.89 380	38.21 414	85.04 351	87.69 297

OpenMVS_ROB	70.19 17	77.77 255	77.46 255	78.71 269	84.39 293	61.15 283	81.18 249	82.52 291	62.45 300	83.34 252	87.37 275	66.20 259	88.66 260	64.69 287	85.02 352	86.32 310

KD-MVS_2432*1600		66.87 355	65.81 361	70.04 351	67.50 417	47.49 388	62.56 400	79.16 313	61.21 318	77.98 322	80.61 360	25.29 425	82.48 335	53.02 363	84.92 353	80.16 387

miper_refine_blended		66.87 355	65.81 361	70.04 351	67.50 417	47.49 388	62.56 400	79.16 313	61.21 318	77.98 322	80.61 360	25.29 425	82.48 335	53.02 363	84.92 353	80.16 387

test_fmvs1_n		70.94 324	70.41 327	72.53 338	73.92 397	66.93 218	75.99 328	84.21 280	43.31 409	79.40 310	79.39 373	43.47 386	68.55 393	69.05 246	84.91 355	82.10 368

test-LLR		67.21 352	66.74 356	68.63 365	76.45 382	55.21 343	67.89 383	67.14 391	62.43 302	65.08 403	72.39 405	43.41 387	69.37 386	61.00 315	84.89 356	81.31 376

test-mter		65.00 366	63.79 370	68.63 365	76.45 382	55.21 343	67.89 383	67.14 391	50.98 386	65.08 403	72.39 405	28.27 419	69.37 386	61.00 315	84.89 356	81.31 376

PS-MVSNAJ		77.04 262	76.53 266	78.56 271	87.09 238	61.40 279	75.26 336	87.13 228	61.25 316	74.38 357	77.22 391	76.94 167	90.94 199	64.63 288	84.83 358	83.35 351

xiu_mvs_v2_base		77.19 260	76.75 264	78.52 272	87.01 240	61.30 281	75.55 334	87.12 231	61.24 317	74.45 355	78.79 378	77.20 161	90.93 200	64.62 289	84.80 359	83.32 352

pmmvs3		62.47 372	60.02 385	69.80 354	71.58 411	64.00 245	70.52 373	58.44 416	39.77 415	66.05 396	75.84 398	27.10 424	72.28 377	46.15 396	84.77 360	73.11 401

MDTV_nov1_ep13			68.29 348		78.03 366	43.87 404	74.12 345	72.22 364	52.17 376	67.02 394	85.54 303	45.36 375	80.85 345	55.73 343	84.42 361

test_fmvs1		69.57 339	69.05 339	71.14 348	69.15 416	65.77 230	73.98 347	83.32 284	42.83 411	77.77 327	78.27 382	43.39 389	68.50 394	68.39 256	84.38 362	79.15 391

1112_ss		74.82 289	73.74 290	78.04 283	89.57 172	60.04 296	76.49 320	87.09 232	54.31 364	73.66 361	79.80 369	60.25 293	86.76 288	58.37 329	84.15 363	87.32 301

testing11		67.38 351	65.93 359	71.73 344	83.37 311	46.60 392	70.95 370	69.40 381	62.47 299	66.14 395	76.66 394	31.22 412	84.10 325	49.10 383	84.10 364	84.49 330

PatchMatch-RL		74.48 292	73.22 298	78.27 279	87.70 220	85.26 38	75.92 329	70.09 377	64.34 288	76.09 340	81.25 357	65.87 262	78.07 362	53.86 357	83.82 365	71.48 403

UBG		64.34 370	63.35 372	67.30 372	83.50 306	40.53 411	67.46 387	65.02 399	54.77 362	67.54 393	74.47 403	32.99 410	78.50 361	40.82 407	83.58 366	82.88 358

MDA-MVSNet_test_wron		70.05 333	70.44 325	68.88 362	73.84 398	53.47 355	58.93 410	67.28 389	58.43 336	87.09 167	85.40 308	59.80 298	67.25 399	59.66 324	83.54 367	85.92 315

YYNet1		70.06 332	70.44 325	68.90 361	73.76 399	53.42 357	58.99 409	67.20 390	58.42 337	87.10 166	85.39 309	59.82 297	67.32 398	59.79 323	83.50 368	85.96 313

Test_1112_low_res		73.90 298	73.08 299	76.35 306	90.35 159	55.95 334	73.40 354	86.17 243	50.70 388	73.14 362	85.94 299	58.31 307	85.90 305	56.51 339	83.22 369	87.20 302

PVSNet	58.17 21	66.41 360	65.63 363	68.75 363	81.96 326	49.88 381	62.19 402	72.51 362	51.03 385	68.04 389	75.34 401	50.84 345	74.77 373	45.82 398	82.96 370	81.60 373

gg-mvs-nofinetune		68.96 345	69.11 338	68.52 367	76.12 385	45.32 398	83.59 193	55.88 418	86.68 29	64.62 407	97.01 9	30.36 414	83.97 328	44.78 400	82.94 371	76.26 396

CR-MVSNet		74.00 297	73.04 300	76.85 301	79.58 354	62.64 262	82.58 221	76.90 329	50.50 390	75.72 344	92.38 153	48.07 356	84.07 326	68.72 252	82.91 372	83.85 343

RPMNet		78.88 241	78.28 250	80.68 244	79.58 354	62.64 262	82.58 221	94.16 32	74.80 160	75.72 344	92.59 146	48.69 353	95.56 42	73.48 201	82.91 372	83.85 343

test_vis1_n		70.29 328	69.99 332	71.20 347	75.97 386	66.50 222	76.69 315	80.81 306	44.22 405	75.43 347	77.23 390	50.00 350	68.59 392	66.71 266	82.85 374	78.52 393

test0.0.03 1		64.66 368	64.36 367	65.57 380	75.03 394	46.89 391	64.69 396	61.58 410	62.43 302	71.18 373	77.54 386	43.41 387	68.47 395	40.75 408	82.65 375	81.35 375

HY-MVS	64.64 18	73.03 305	72.47 309	74.71 321	83.36 312	54.19 350	82.14 238	81.96 296	56.76 353	69.57 383	86.21 296	60.03 294	84.83 317	49.58 381	82.65 375	85.11 324

SCA		73.32 301	72.57 307	75.58 315	81.62 331	55.86 337	78.89 282	71.37 372	61.73 307	74.93 353	83.42 334	60.46 290	87.01 279	58.11 333	82.63 377	83.88 340

test_f		64.31 371	65.85 360	59.67 396	66.54 420	62.24 273	57.76 412	70.96 374	40.13 414	84.36 227	82.09 348	46.93 358	51.67 420	61.99 308	81.89 378	65.12 411

CHOSEN 1792x2688		72.45 309	70.56 323	78.13 280	90.02 169	63.08 255	68.72 381	83.16 285	42.99 410	75.92 342	85.46 306	57.22 316	85.18 314	49.87 379	81.67 379	86.14 312

WTY-MVS		67.91 350	68.35 347	66.58 376	80.82 343	48.12 385	65.96 393	72.60 360	53.67 367	71.20 372	81.68 354	58.97 303	69.06 390	48.57 386	81.67 379	82.55 362

TESTMET0.1,1		61.29 377	60.32 383	64.19 385	72.06 409	51.30 372	67.89 383	62.09 403	45.27 401	60.65 412	69.01 411	27.93 420	64.74 408	56.31 340	81.65 381	76.53 395

dmvs_re		66.81 357	66.98 353	66.28 377	76.87 376	58.68 316	71.66 364	72.24 363	60.29 327	69.52 384	73.53 404	52.38 338	64.40 409	44.90 399	81.44 382	75.76 397

PAPM		71.77 315	70.06 330	76.92 298	86.39 250	53.97 351	76.62 317	86.62 238	53.44 368	63.97 408	84.73 320	57.79 313	92.34 161	39.65 409	81.33 383	84.45 332

DSMNet-mixed		60.98 380	61.61 380	59.09 398	72.88 406	45.05 400	74.70 341	46.61 424	26.20 422	65.34 401	90.32 221	55.46 326	63.12 411	41.72 405	81.30 384	69.09 407

sss		66.92 354	67.26 352	65.90 378	77.23 372	51.10 376	64.79 395	71.72 370	52.12 379	70.13 380	80.18 366	57.96 310	65.36 407	50.21 376	81.01 385	81.25 378

tpm		67.95 349	68.08 350	67.55 370	78.74 365	43.53 405	75.60 331	67.10 393	54.92 360	72.23 367	88.10 259	42.87 391	75.97 369	52.21 368	80.95 386	83.15 355

MonoMVSNet		76.66 267	77.26 259	74.86 319	79.86 352	54.34 349	86.26 137	86.08 245	71.08 217	85.59 201	88.68 251	53.95 332	85.93 302	63.86 293	80.02 387	84.32 334

tpm2		68.45 348	66.83 355	73.30 329	78.93 364	48.50 383	79.76 266	71.76 369	47.50 394	69.92 381	83.60 330	42.07 392	88.40 263	48.44 388	79.51 388	83.01 357

FPMVS		72.29 312	72.00 311	73.14 330	88.63 198	85.00 40	74.65 342	67.39 388	71.94 208	77.80 326	87.66 269	50.48 348	75.83 370	49.95 377	79.51 388	58.58 417

UnsupCasMVSNet_bld		69.21 343	69.68 334	67.82 369	79.42 357	51.15 374	67.82 386	75.79 336	54.15 365	77.47 330	85.36 311	59.26 301	70.64 384	48.46 387	79.35 390	81.66 372

CostFormer		69.98 335	68.68 345	73.87 324	77.14 373	50.72 377	79.26 275	74.51 345	51.94 380	70.97 374	84.75 319	45.16 379	87.49 274	55.16 351	79.23 391	83.40 350

1314		73.22 303	72.56 308	75.20 316	80.41 349	57.84 322	81.64 242	85.36 257	51.68 381	73.10 363	76.65 395	61.45 285	85.19 313	63.54 296	79.21 392	82.59 360

test_vis1_n_1920		71.30 322	71.58 316	70.47 349	77.58 370	59.99 298	74.25 343	84.22 279	51.06 384	74.85 354	79.10 375	55.10 329	68.83 391	68.86 249	79.20 393	82.58 361

baseline1		73.26 302	73.54 293	72.43 339	84.92 282	47.79 387	79.89 265	74.00 348	65.93 269	78.81 317	86.28 295	56.36 320	81.63 341	56.63 338	79.04 394	87.87 295

PMMVS		61.65 375	60.38 382	65.47 381	65.40 424	69.26 192	63.97 398	61.73 408	36.80 421	60.11 413	68.43 412	59.42 299	66.35 403	48.97 384	78.57 395	60.81 414

baseline2		69.77 337	66.89 354	78.41 275	79.51 356	58.09 318	76.23 324	69.57 380	57.50 346	64.82 406	77.45 388	46.02 364	88.44 262	53.08 362	77.83 396	88.70 280

test_vis1_rt		65.64 364	64.09 368	70.31 350	66.09 421	70.20 181	61.16 403	81.60 300	38.65 417	72.87 364	69.66 410	52.84 335	60.04 414	56.16 341	77.77 397	80.68 385

MS-PatchMatch		70.93 325	70.22 328	73.06 331	81.85 328	62.50 265	73.82 350	77.90 319	52.44 375	75.92 342	81.27 356	55.67 325	81.75 339	55.37 348	77.70 398	74.94 399

UnsupCasMVSNet_eth		71.63 318	72.30 310	69.62 356	76.47 381	52.70 362	70.03 377	80.97 305	59.18 332	79.36 311	88.21 258	60.50 289	69.12 389	58.33 331	77.62 399	87.04 303

CVMVSNet		72.62 308	71.41 318	76.28 308	83.25 315	60.34 294	83.50 195	79.02 316	37.77 420	76.33 335	85.10 313	49.60 352	87.41 275	70.54 230	77.54 400	81.08 381

test_cas_vis1_n_1920		69.20 344	69.12 337	69.43 358	73.68 400	62.82 259	70.38 375	77.21 326	46.18 399	80.46 300	78.95 377	52.03 339	65.53 406	65.77 277	77.45 401	79.95 389

GG-mvs-BLEND				67.16 373	73.36 401	46.54 394	84.15 176	55.04 419		58.64 417	61.95 418	29.93 415	83.87 329	38.71 412	76.92 402	71.07 404

CHOSEN 280x420		59.08 383	56.52 388	66.76 375	76.51 380	64.39 241	49.62 417	59.00 414	43.86 406	55.66 421	68.41 413	35.55 405	68.21 397	43.25 402	76.78 403	67.69 409

tpmvs		70.16 330	69.56 335	71.96 342	74.71 396	48.13 384	79.63 267	75.45 341	65.02 285	70.26 379	81.88 351	45.34 376	85.68 309	58.34 330	75.39 404	82.08 369

MVP-Stereo		75.81 278	73.51 294	82.71 206	89.35 178	73.62 134	80.06 261	85.20 260	60.30 326	73.96 358	87.94 262	57.89 312	89.45 245	52.02 369	74.87 405	85.06 325
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
new_pmnet		55.69 386	57.66 387	49.76 402	75.47 390	30.59 422	59.56 405	51.45 421	43.62 408	62.49 409	75.48 400	40.96 394	49.15 422	37.39 415	72.52 406	69.55 406

mvsany_test3		65.48 365	62.97 374	73.03 332	69.99 414	76.17 121	64.83 394	43.71 425	43.68 407	80.25 304	87.05 284	52.83 336	63.09 412	51.92 373	72.44 407	79.84 390

PatchmatchNet		69.71 338	68.83 343	72.33 341	77.66 369	53.60 354	79.29 274	69.99 378	57.66 344	72.53 366	82.93 339	46.45 361	80.08 352	60.91 317	72.09 408	83.31 353
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MVS-HIRNet		61.16 378	62.92 375	55.87 399	79.09 361	35.34 420	71.83 362	57.98 417	46.56 397	59.05 415	91.14 191	49.95 351	76.43 367	38.74 411	71.92 409	55.84 418

tpmrst		66.28 361	66.69 357	65.05 383	72.82 407	39.33 413	78.20 291	70.69 376	53.16 371	67.88 390	80.36 365	48.18 355	74.75 374	58.13 332	70.79 410	81.08 381

tpm cat1		66.76 358	65.21 366	71.42 345	77.09 374	50.62 378	78.01 292	73.68 354	44.89 403	68.64 386	79.00 376	45.51 373	82.42 337	49.91 378	70.15 411	81.23 380

ADS-MVSNet2		65.87 363	63.64 371	72.55 337	73.16 403	56.92 330	67.10 389	74.81 342	49.74 392	66.04 397	82.97 337	46.71 359	77.26 365	42.29 403	69.96 412	83.46 348

ADS-MVSNet		61.90 374	62.19 378	61.03 394	73.16 403	36.42 419	67.10 389	61.75 407	49.74 392	66.04 397	82.97 337	46.71 359	63.21 410	42.29 403	69.96 412	83.46 348

JIA-IIPM		69.41 340	66.64 358	77.70 289	73.19 402	71.24 172	75.67 330	65.56 397	70.42 222	65.18 402	92.97 133	33.64 409	83.06 331	53.52 361	69.61 414	78.79 392

dmvs_testset		60.59 382	62.54 377	54.72 401	77.26 371	27.74 424	74.05 346	61.00 411	60.48 325	65.62 400	67.03 414	55.93 323	68.23 396	32.07 421	69.46 415	68.17 408

EPMVS		62.47 372	62.63 376	62.01 389	70.63 413	38.74 415	74.76 340	52.86 420	53.91 366	67.71 392	80.01 367	39.40 396	66.60 402	55.54 347	68.81 416	80.68 385

MVE	40.22 23	51.82 388	50.47 391	55.87 399	62.66 426	51.91 367	31.61 420	39.28 427	40.65 413	50.76 422	74.98 402	56.24 322	44.67 423	33.94 419	64.11 417	71.04 405
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dp		60.70 381	60.29 384	61.92 391	72.04 410	38.67 416	70.83 371	64.08 401	51.28 383	60.75 411	77.28 389	36.59 404	71.58 382	47.41 391	62.34 418	75.52 398

mvsany_test1		58.48 384	56.47 389	64.50 384	65.90 423	68.21 205	56.95 413	42.11 426	38.30 418	65.69 399	77.19 392	56.96 317	59.35 416	46.16 395	58.96 419	65.93 410

PVSNet_0	51.08 22	56.10 385	54.97 390	59.48 397	75.12 393	53.28 358	55.16 414	61.89 406	44.30 404	59.16 414	62.48 417	54.22 331	65.91 405	35.40 416	47.01 420	59.25 416

tmp_tt		20.25 393	24.50 396	7.49 408	4.47 431	8.70 432	34.17 419	25.16 429	1.00 426	32.43 425	18.49 423	39.37 397	9.21 427	21.64 423	43.75 421	4.57 423

test_method		30.46 391	29.60 394	33.06 405	17.99 430	3.84 433	13.62 421	73.92 349	2.79 424	18.29 426	53.41 419	28.53 418	43.25 424	22.56 422	35.27 422	52.11 419

DeepMVS_CX				24.13 407	32.95 429	29.49 423		21.63 430	12.07 423	37.95 424	45.07 421	30.84 413	19.21 426	17.94 425	33.06 423	23.69 422

dongtai		41.90 389	42.65 392	39.67 404	70.86 412	21.11 426	61.01 404	21.42 431	57.36 347	57.97 419	50.06 420	16.40 430	58.73 417	21.03 424	27.69 424	39.17 420

kuosan		30.83 390	32.17 393	26.83 406	53.36 428	19.02 429	57.90 411	20.44 432	38.29 419	38.01 423	37.82 422	15.18 431	33.45 425	7.74 426	20.76 425	28.03 421

testmvs		5.91 397	7.65 400	0.72 410	1.20 432	0.37 435	59.14 407	0.67 434	0.49 428	1.11 428	2.76 427	0.94 433	0.24 429	1.02 428	1.47 426	1.55 425

test123		6.27 396	8.08 399	0.84 409	1.11 433	0.57 434	62.90 399	0.82 433	0.54 427	1.07 429	2.75 428	1.26 432	0.30 428	1.04 427	1.26 427	1.66 424

mmdepth		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

monomultidepth		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

test_blank		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uanet_test		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

DCPMVS		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

cdsmvs_eth3d_5k		20.81 392	27.75 395	0.00 411	0.00 434	0.00 436	0.00 422	85.44 256	0.00 429	0.00 430	82.82 341	81.46 119	0.00 430	0.00 429	0.00 428	0.00 426

pcd_1.5k_mvsjas		6.41 395	8.55 398	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	76.94 167	0.00 430	0.00 429	0.00 428	0.00 426

sosnet-low-res		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

sosnet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uncertanet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

Regformer		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

ab-mvs-re		6.65 394	8.87 397	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	79.80 369	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uanet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

WAC-MVS						37.39 417								52.61 367

FOURS1					96.08 12	87.41 14	96.19 2	95.83 5	92.95 3	96.57 3

test_one_0601					93.85 62	73.27 140		94.11 38	86.57 30	93.47 41	94.64 64	88.42 28

eth-test2					0.00 434

eth-test					0.00 434

test_241102_ONE					94.18 50	72.65 145		93.69 56	83.62 54	94.11 26	93.78 108	90.28 14	95.50 49

save fliter					93.75 63	77.44 103	86.31 135	89.72 187	70.80 219

test0726					94.16 53	72.56 151	90.63 49	93.90 48	83.61 55	93.75 34	94.49 69	89.76 18

GSMVS																83.88 340

test_part2					93.86 61	77.77 98				92.84 51

sam_mvs1												46.11 363				83.88 340

sam_mvs												45.92 368

MTGPA								91.81 127

test_post1							78.85 284				3.13 425	45.19 378	80.13 351	58.11 333

test_post											3.10 426	45.43 374	77.22 366

patchmatchnet-post											81.71 353	45.93 367	87.01 279

MTMP							90.66 48	33.14 428

gm-plane-assit					75.42 391	44.97 401			52.17 376		72.36 407		87.90 269	54.10 356

TEST9					92.34 98	79.70 78	83.94 181	90.32 169	65.41 281	84.49 223	90.97 197	82.03 110	93.63 115

test_8					92.09 107	78.87 85	83.82 186	90.31 171	65.79 272	84.36 227	90.96 199	81.93 112	93.44 128

agg_prior					91.58 127	77.69 100		90.30 172		84.32 229			93.18 136

test_prior4						78.97 84	84.59 167

test_prior				86.32 110	90.59 155	71.99 162		92.85 93					94.17 97			92.80 160

旧先验2							81.73 240		56.88 352	86.54 185			84.90 316	72.81 212

新几何2							81.72 241

无先验							82.81 216	85.62 254	58.09 340				91.41 187	67.95 260		84.48 331

原ACMM2							82.26 234

testdata2													86.43 293	63.52 297

segment_acmp												81.94 111

testdata1							79.62 268		73.95 169

plane_prior7					93.45 68	77.31 106

plane_prior6					92.61 90	76.54 113						74.84 188

plane_prior4											92.95 134

plane_prior3						76.85 111			77.79 125	86.55 180

plane_prior2							89.45 82		79.44 101

plane_prior1					92.83 88

n2								0.00 435

nn								0.00 435

door-mid								74.45 346

test11								91.46 133

door								72.57 361

HQP5-MVS						70.66 175

HQP-NCC					91.19 139		84.77 161		73.30 183	80.55 297

ACMP_Plane					91.19 139		84.77 161		73.30 183	80.55 297

BP-MVS														77.30 155

HQP4-MVS										80.56 296			94.61 79			93.56 133

HQP2-MVS												72.10 225

NP-MVS					91.95 112	74.55 129					90.17 228

MDTV_nov1_ep13_2view						27.60 425	70.76 372		46.47 398	61.27 410		45.20 377		49.18 382		83.75 345

Test By Simon												79.09 141

High-resolution multi-view benchmark