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.

lecture		95.10 11	95.46 8	94.01 61	98.40 23	84.36 102	97.70 3	97.78 1	91.19 19	96.22 29	98.08 17	86.64 40	99.37 33	94.91 41	98.26 59	98.29 56

PGM-MVS		93.96 53	93.72 65	94.68 38	98.43 20	86.22 47	95.30 121	97.78 1	87.45 146	93.26 78	97.33 50	84.62 74	99.51 24	90.75 125	98.57 49	98.32 50

test_fmvsm_n_1920		94.71 23	95.11 15	93.50 80	95.79 127	84.62 87	96.15 57	97.64 3	89.85 54	97.19 13	97.89 31	86.28 47	98.71 115	97.11 14	98.08 74	97.17 141

FC-MVSNet-test		90.27 147	90.18 135	90.53 236	93.71 258	79.85 255	95.77 92	97.59 4	89.31 77	86.27 241	94.67 186	81.93 118	97.01 285	84.26 218	88.09 292	94.71 265

fmvsm_s_conf0.5_n_8		94.56 26	95.12 14	92.87 112	95.96 122	81.32 201	95.76 94	97.57 5	93.48 2	97.53 9	98.32 2	81.78 121	99.13 56	97.91 2	97.81 85	98.16 70

FIs		90.51 143	90.35 130	90.99 220	93.99 240	80.98 216	95.73 96	97.54 6	89.15 84	86.72 230	94.68 183	81.83 119	97.24 267	85.18 201	88.31 289	94.76 264

DPE-MVS		95.57 4	95.67 4	95.25 11	98.36 27	87.28 18	95.56 111	97.51 7	89.13 85	97.14 14	97.91 30	91.64 7	99.62 2	94.61 45	99.17 2	98.86 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS++		95.98 1	96.36 1	94.82 31	97.78 56	86.00 52	98.29 1	97.49 8	90.75 27	97.62 7	98.06 20	92.59 2	99.61 4	95.64 30	99.02 12	98.86 12

FOURS1					98.86 1	85.54 69	98.29 1	97.49 8	89.79 61	96.29 27

test_0728_SECOND				95.01 17	98.79 2	86.43 39	97.09 17	97.49 8					99.61 4	95.62 32	99.08 7	98.99 9

PHI-MVS		93.89 55	93.65 69	94.62 41	96.84 80	86.43 39	96.69 33	97.49 8	85.15 217	93.56 75	96.28 99	85.60 55	99.31 43	92.45 77	98.79 24	98.12 76

SF-MVS		94.97 14	94.90 24	95.20 12	97.84 52	87.76 10	96.65 35	97.48 12	87.76 138	95.71 38	97.70 38	88.28 23	99.35 37	93.89 53	98.78 26	98.48 31

test0726					98.78 3	85.93 57	97.19 12	97.47 13	90.27 43	97.64 5	98.13 6	91.47 8

MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 36	96.91 26	97.47 13	91.73 13	96.10 31	96.69 81	89.90 12	99.30 44	94.70 43	98.04 75	99.13 2
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
UniMVSNet (Re)		89.80 166	89.07 170	92.01 162	93.60 264	84.52 92	94.78 162	97.47 13	89.26 80	86.44 237	92.32 276	82.10 113	97.39 255	84.81 207	80.84 378	94.12 292

ACMMP		93.24 79	92.88 85	94.30 55	98.09 40	85.33 74	96.86 28	97.45 16	88.33 113	90.15 161	97.03 68	81.44 122	99.51 24	90.85 124	95.74 136	98.04 84
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
test_one_0601					98.58 11	85.83 63		97.44 17	91.05 21	96.78 23	98.06 20	91.45 11

SED-MVS		95.91 2	96.28 2	94.80 33	98.77 5	85.99 54	97.13 15	97.44 17	90.31 39	97.71 2	98.07 18	92.31 4	99.58 10	95.66 28	99.13 3	98.84 15

test_241102_TWO								97.44 17	90.31 39	97.62 7	98.07 18	91.46 10	99.58 10	95.66 28	99.12 6	98.98 10

test_241102_ONE					98.77 5	85.99 54		97.44 17	90.26 45	97.71 2	97.96 29	92.31 4	99.38 31

9.14			94.47 30		97.79 54		96.08 64	97.44 17	86.13 185	95.10 48	97.40 47	88.34 22	99.22 48	93.25 62	98.70 34

APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 30	86.29 46	97.46 7	97.40 22	89.03 90	96.20 30	98.10 12	89.39 16	99.34 38	95.88 27	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CSCG		93.23 80	93.05 81	93.76 73	98.04 42	84.07 108	96.22 51	97.37 23	84.15 240	90.05 162	95.66 136	87.77 26	99.15 55	89.91 135	98.27 58	98.07 78

fmvsm_l_conf0.5_n_3		94.80 20	95.01 17	94.15 59	95.64 136	85.08 77	96.09 63	97.36 24	90.98 22	97.09 16	98.12 9	84.98 69	98.94 86	97.07 15	97.80 86	98.43 39

test_fmvsmconf_n		94.60 25	94.81 25	93.98 62	94.62 197	84.96 80	96.15 57	97.35 25	89.37 74	96.03 34	98.11 10	86.36 45	99.01 69	97.45 9	97.83 84	97.96 88

ACMMP_NAP		94.74 22	94.56 28	95.28 10	98.02 43	87.70 11	95.68 99	97.34 26	88.28 116	95.30 44	97.67 39	85.90 51	99.54 20	93.91 52	98.95 15	98.60 24

HFP-MVS		94.52 27	94.40 33	94.86 24	98.61 10	86.81 25	96.94 21	97.34 26	88.63 104	93.65 71	97.21 56	86.10 49	99.49 26	92.35 83	98.77 28	98.30 51

MSLP-MVS++		93.72 61	94.08 50	92.65 129	97.31 70	83.43 129	95.79 90	97.33 28	90.03 48	93.58 73	96.96 70	84.87 70	97.76 208	92.19 90	98.66 41	96.76 176

VPA-MVSNet		89.62 169	88.96 174	91.60 190	93.86 246	82.89 155	95.46 113	97.33 28	87.91 129	88.43 192	93.31 242	74.17 225	97.40 252	87.32 172	82.86 349	94.52 274

ZNCC-MVS		94.47 29	94.28 40	95.03 16	98.52 15	86.96 20	96.85 29	97.32 30	88.24 117	93.15 81	97.04 67	86.17 48	99.62 2	92.40 80	98.81 23	98.52 27

ACMMPR		94.43 32	94.28 40	94.91 21	98.63 9	86.69 28	96.94 21	97.32 30	88.63 104	93.53 76	97.26 54	85.04 64	99.54 20	92.35 83	98.78 26	98.50 28

WR-MVS_H		87.80 228	87.37 219	89.10 301	93.23 273	78.12 298	95.61 107	97.30 32	87.90 130	83.72 318	92.01 292	79.65 146	96.01 344	76.36 334	80.54 382	93.16 344

SteuartSystems-ACMMP		95.20 8	95.32 11	94.85 25	96.99 77	86.33 42	97.33 8	97.30 32	91.38 18	95.39 42	97.46 44	88.98 19	99.40 30	94.12 49	98.89 18	98.82 17
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_s_conf0.5_n_6		94.11 47	94.56 28	92.76 120	94.98 169	81.96 184	95.79 90	97.29 34	89.31 77	97.52 10	97.61 40	83.25 90	98.88 92	97.05 17	98.22 65	97.43 125

SMA-MVS		95.20 8	95.07 16	95.59 6	98.14 37	88.48 8	96.26 49	97.28 35	85.90 187	97.67 4	98.10 12	88.41 20	99.56 12	94.66 44	99.19 1	98.71 21
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
CP-MVS		94.34 35	94.21 45	94.74 37	98.39 25	86.64 32	97.60 5	97.24 36	88.53 109	92.73 97	97.23 55	85.20 61	99.32 42	92.15 91	98.83 22	98.25 64

MVS_111021_HR		93.45 69	93.31 74	93.84 68	96.99 77	84.84 81	93.24 266	97.24 36	88.76 99	91.60 132	95.85 126	86.07 50	98.66 117	91.91 103	98.16 67	98.03 85

region2R		94.43 32	94.27 42	94.92 20	98.65 8	86.67 30	96.92 25	97.23 38	88.60 107	93.58 73	97.27 52	85.22 60	99.54 20	92.21 88	98.74 31	98.56 26

reproduce_model		94.76 21	94.92 21	94.29 56	97.92 45	85.18 76	95.95 79	97.19 39	89.67 65	95.27 45	98.16 5	86.53 44	99.36 36	95.42 35	98.15 68	98.33 46

patch_mono-2		93.74 60	94.32 36	92.01 162	97.54 62	78.37 292	93.40 253	97.19 39	88.02 125	94.99 50	97.21 56	88.35 21	98.44 145	94.07 50	98.09 72	99.23 1

GST-MVS		94.21 40	93.97 55	94.90 23	98.41 22	86.82 24	96.54 37	97.19 39	88.24 117	93.26 78	96.83 76	85.48 57	99.59 8	91.43 114	98.40 54	98.30 51

XVS		94.45 30	94.32 36	94.85 25	98.54 13	86.60 34	96.93 23	97.19 39	90.66 32	92.85 89	97.16 62	85.02 65	99.49 26	91.99 99	98.56 50	98.47 34

X-MVStestdata		88.31 215	86.13 264	94.85 25	98.54 13	86.60 34	96.93 23	97.19 39	90.66 32	92.85 89	23.41 462	85.02 65	99.49 26	91.99 99	98.56 50	98.47 34

MP-MVS-pluss		94.21 40	94.00 54	94.85 25	98.17 35	86.65 31	94.82 159	97.17 44	86.26 179	92.83 91	97.87 32	85.57 56	99.56 12	94.37 48	98.92 17	98.34 44
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
fmvsm_s_conf0.5_n_3		94.49 28	95.13 13	92.56 134	95.49 144	81.10 211	95.93 80	97.16 45	92.96 4	97.39 11	98.13 6	83.63 84	98.80 104	97.89 3	97.61 93	97.78 104

reproduce-ours		94.82 17	94.97 18	94.38 50	97.91 49	85.46 70	95.86 84	97.15 46	89.82 55	95.23 46	98.10 12	87.09 37	99.37 33	95.30 36	98.25 63	98.30 51

our_new_method		94.82 17	94.97 18	94.38 50	97.91 49	85.46 70	95.86 84	97.15 46	89.82 55	95.23 46	98.10 12	87.09 37	99.37 33	95.30 36	98.25 63	98.30 51

fmvsm_s_conf0.5_n_7		93.15 84	93.76 63	91.31 202	94.42 215	79.48 262	94.52 178	97.14 48	89.33 76	94.17 59	98.09 16	81.83 119	97.49 233	96.33 24	98.02 76	96.95 162

DELS-MVS		93.43 74	93.25 76	93.97 63	95.42 146	85.04 78	93.06 275	97.13 49	90.74 29	91.84 124	95.09 165	86.32 46	99.21 49	91.22 115	98.45 52	97.65 112
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
fmvsm_l_conf0.5_n_9		94.65 24	95.28 12	92.77 118	95.95 123	81.83 186	95.53 112	97.12 50	91.68 15	97.89 1	98.06 20	85.71 53	98.65 119	97.32 11	98.26 59	97.83 100

MCST-MVS		94.45 30	94.20 46	95.19 13	98.46 19	87.50 16	95.00 146	97.12 50	87.13 154	92.51 106	96.30 98	89.24 17	99.34 38	93.46 57	98.62 46	98.73 19

UniMVSNet_NR-MVSNet		89.92 162	89.29 164	91.81 183	93.39 270	83.72 119	94.43 186	97.12 50	89.80 58	86.46 234	93.32 241	83.16 91	97.23 268	84.92 204	81.02 374	94.49 279

SD-MVS		94.96 15	95.33 10	93.88 66	97.25 74	86.69 28	96.19 52	97.11 53	90.42 35	96.95 20	97.27 52	89.53 14	96.91 292	94.38 47	98.85 20	98.03 85
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
DeepPCF-MVS	89.96 1	94.20 42	94.77 26	92.49 139	96.52 93	80.00 250	94.00 223	97.08 54	90.05 47	95.65 40	97.29 51	89.66 13	98.97 81	93.95 51	98.71 32	98.50 28

ZD-MVS					98.15 36	86.62 33		97.07 55	83.63 253	94.19 58	96.91 72	87.57 31	99.26 46	91.99 99	98.44 53

HPM-MVS		94.02 49	93.88 56	94.43 47	98.39 25	85.78 65	97.25 11	97.07 55	86.90 163	92.62 103	96.80 80	84.85 71	99.17 51	92.43 78	98.65 44	98.33 46
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
3Dnovator	86.66 5	91.73 110	90.82 125	94.44 45	94.59 199	86.37 41	97.18 13	97.02 57	89.20 82	84.31 306	96.66 84	73.74 235	99.17 51	86.74 179	97.96 78	97.79 103

DeepC-MVS	88.79 3	93.31 76	92.99 83	94.26 57	96.07 113	85.83 63	94.89 152	96.99 58	89.02 91	89.56 168	97.37 49	82.51 102	99.38 31	92.20 89	98.30 57	97.57 117
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		94.25 37	94.07 51	94.77 35	98.47 18	86.31 44	96.71 32	96.98 59	89.04 88	91.98 117	97.19 59	85.43 58	99.56 12	92.06 97	98.79 24	98.44 38
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
fmvsm_s_conf0.5_n_4		93.86 56	94.37 35	92.33 152	95.13 162	80.95 218	95.64 105	96.97 60	89.60 67	96.85 21	97.77 36	83.08 94	98.92 89	97.49 7	96.78 113	97.13 147

MTGPA								96.97 60

MTAPA		94.42 34	94.22 43	95.00 18	98.42 21	86.95 21	94.36 196	96.97 60	91.07 20	93.14 82	97.56 41	84.30 77	99.56 12	93.43 58	98.75 30	98.47 34

HPM-MVS++		95.14 10	94.91 22	95.83 4	98.25 31	89.65 4	95.92 81	96.96 63	91.75 12	94.02 65	96.83 76	88.12 24	99.55 16	93.41 60	98.94 16	98.28 57

CNVR-MVS		95.40 7	95.37 9	95.50 8	98.11 38	88.51 7	95.29 123	96.96 63	92.09 9	95.32 43	97.08 64	89.49 15	99.33 41	95.10 39	98.85 20	98.66 22

CS-MVS		94.12 46	94.44 32	93.17 93	96.55 90	83.08 147	97.63 4	96.95 65	91.71 14	93.50 77	96.21 101	85.61 54	98.24 162	93.64 55	98.17 66	98.19 67

APD-MVS		94.24 38	94.07 51	94.75 36	98.06 41	86.90 23	95.88 83	96.94 66	85.68 194	95.05 49	97.18 60	87.31 35	99.07 59	91.90 105	98.61 48	98.28 57
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		94.81 19	94.69 27	95.17 14	97.83 53	87.46 17	95.66 102	96.93 67	92.34 7	93.94 66	96.58 91	87.74 27	99.44 29	92.83 69	98.40 54	98.62 23

fmvsm_s_conf0.5_n_9		94.99 13	95.50 7	93.44 81	96.51 95	82.25 177	95.76 94	96.92 68	93.37 3	97.63 6	98.43 1	84.82 72	99.16 54	98.15 1	97.92 80	98.90 11

SPE-MVS-test		94.02 49	94.29 39	93.24 88	96.69 83	83.24 136	97.49 6	96.92 68	92.14 8	92.90 87	95.77 132	85.02 65	98.33 157	93.03 66	98.62 46	98.13 73

mPP-MVS		93.99 51	93.78 61	94.63 40	98.50 16	85.90 62	96.87 27	96.91 70	88.70 102	91.83 126	97.17 61	83.96 81	99.55 16	91.44 113	98.64 45	98.43 39

SR-MVS		94.23 39	94.17 49	94.43 47	98.21 34	85.78 65	96.40 39	96.90 71	88.20 120	94.33 55	97.40 47	84.75 73	99.03 64	93.35 61	97.99 77	98.48 31

DeepC-MVS_fast	89.43 2	94.04 48	93.79 60	94.80 33	97.48 66	86.78 26	95.65 104	96.89 72	89.40 73	92.81 92	96.97 69	85.37 59	99.24 47	90.87 123	98.69 35	98.38 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_prior				93.82 69	97.29 72	84.49 93		96.88 73					98.87 93			98.11 77

APD-MVS_3200maxsize		93.78 58	93.77 62	93.80 71	97.92 45	84.19 106	96.30 42	96.87 74	86.96 159	93.92 67	97.47 43	83.88 82	98.96 83	92.71 73	97.87 82	98.26 63

MSC_two_6792asdad				96.52 1	97.78 56	90.86 1		96.85 75					99.61 4	96.03 25	99.06 9	99.07 5

No_MVS				96.52 1	97.78 56	90.86 1		96.85 75					99.61 4	96.03 25	99.06 9	99.07 5

IU-MVS					98.77 5	86.00 52		96.84 77	81.26 318	97.26 12				95.50 34	99.13 3	99.03 8

PVSNet_BlendedMVS		89.98 157	89.70 150	90.82 228	96.12 106	81.25 203	93.92 229	96.83 78	83.49 258	89.10 177	92.26 279	81.04 126	98.85 97	86.72 181	87.86 296	92.35 372

PVSNet_Blended		90.73 132	90.32 131	91.98 166	96.12 106	81.25 203	92.55 294	96.83 78	82.04 292	89.10 177	92.56 269	81.04 126	98.85 97	86.72 181	95.91 132	95.84 220

test_fmvsmconf0.1_n		94.20 42	94.31 38	93.88 66	92.46 304	84.80 83	96.18 54	96.82 80	89.29 79	95.68 39	98.11 10	85.10 62	98.99 76	97.38 10	97.75 90	97.86 97

save fliter					97.85 51	85.63 68	95.21 133	96.82 80	89.44 71

原ACMM1				92.01 162	97.34 69	81.05 213		96.81 82	78.89 348	90.45 152	95.92 120	82.65 100	98.84 99	80.68 285	98.26 59	96.14 203

HPM-MVS_fast		93.40 75	93.22 77	93.94 65	98.36 27	84.83 82	97.15 14	96.80 83	85.77 191	92.47 107	97.13 63	82.38 103	99.07 59	90.51 130	98.40 54	97.92 92

TEST9					97.53 63	86.49 37	94.07 215	96.78 84	81.61 310	92.77 94	96.20 102	87.71 28	99.12 57

train_agg		93.44 70	93.08 80	94.52 44	97.53 63	86.49 37	94.07 215	96.78 84	81.86 301	92.77 94	96.20 102	87.63 29	99.12 57	92.14 92	98.69 35	97.94 89

3Dnovator+	87.14 4	92.42 98	91.37 111	95.55 7	95.63 137	88.73 6	97.07 19	96.77 86	90.84 24	84.02 311	96.62 89	75.95 196	99.34 38	87.77 163	97.68 91	98.59 25

SR-MVS-dyc-post		93.82 57	93.82 58	93.82 69	97.92 45	84.57 89	96.28 46	96.76 87	87.46 144	93.75 69	97.43 45	84.24 78	99.01 69	92.73 70	97.80 86	97.88 95

RE-MVS-def			93.68 67		97.92 45	84.57 89	96.28 46	96.76 87	87.46 144	93.75 69	97.43 45	82.94 96		92.73 70	97.80 86	97.88 95

test_8					97.49 65	86.30 45	94.02 220	96.76 87	81.86 301	92.70 98	96.20 102	87.63 29	99.02 67

RPMNet		83.95 339	81.53 350	91.21 206	90.58 378	79.34 268	85.24 426	96.76 87	71.44 423	85.55 258	82.97 435	70.87 270	98.91 90	61.01 429	89.36 271	95.40 236

fmvsm_s_conf0.5_n_5		93.96 53	94.18 48	93.30 84	94.79 183	83.81 117	95.77 92	96.74 91	88.02 125	96.23 28	97.84 34	83.36 89	98.83 102	97.49 7	97.34 99	97.25 135

EIA-MVS		91.95 103	91.94 100	91.98 166	95.16 159	80.01 249	95.36 116	96.73 92	88.44 110	89.34 173	92.16 281	83.82 83	98.45 143	89.35 140	97.06 103	97.48 121

DVP-MVS		95.67 3	96.02 3	94.64 39	98.78 3	85.93 57	97.09 17	96.73 92	90.27 43	97.04 18	98.05 23	91.47 8	99.55 16	95.62 32	99.08 7	98.45 37
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
agg_prior					97.38 68	85.92 59		96.72 94		92.16 113			98.97 81

EC-MVSNet		93.44 70	93.71 66	92.63 130	95.21 156	82.43 171	97.27 10	96.71 95	90.57 34	92.88 88	95.80 129	83.16 91	98.16 168	93.68 54	98.14 69	97.31 127

QAPM		89.51 173	88.15 199	93.59 79	94.92 174	84.58 88	96.82 30	96.70 96	78.43 359	83.41 327	96.19 105	73.18 244	99.30 44	77.11 327	96.54 119	96.89 168

CANet		93.54 64	93.20 78	94.55 43	95.65 135	85.73 67	94.94 149	96.69 97	91.89 11	90.69 148	95.88 123	81.99 117	99.54 20	93.14 64	97.95 79	98.39 41

CDPH-MVS		92.83 89	92.30 96	94.44 45	97.79 54	86.11 51	94.06 217	96.66 98	80.09 332	92.77 94	96.63 88	86.62 41	99.04 63	87.40 169	98.66 41	98.17 69

PVSNet_Blended_VisFu		91.38 117	90.91 122	92.80 116	96.39 97	83.17 139	94.87 154	96.66 98	83.29 264	89.27 175	94.46 199	80.29 132	99.17 51	87.57 166	95.37 147	96.05 212

DP-MVS Recon		91.95 103	91.28 114	93.96 64	98.33 29	85.92 59	94.66 171	96.66 98	82.69 279	90.03 163	95.82 128	82.30 107	99.03 64	84.57 214	96.48 122	96.91 167

TSAR-MVS + MP.		94.85 16	94.94 20	94.58 42	98.25 31	86.33 42	96.11 62	96.62 101	88.14 122	96.10 31	96.96 70	89.09 18	98.94 86	94.48 46	98.68 37	98.48 31
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PS-CasMVS		87.32 253	86.88 230	88.63 315	92.99 288	76.33 341	95.33 118	96.61 102	88.22 119	83.30 331	93.07 253	73.03 246	95.79 357	78.36 312	81.00 376	93.75 318

DU-MVS		89.34 184	88.50 188	91.85 179	93.04 285	83.72 119	94.47 183	96.59 103	89.50 69	86.46 234	93.29 244	77.25 177	97.23 268	84.92 204	81.02 374	94.59 269

CP-MVSNet		87.63 236	87.26 224	88.74 312	93.12 278	76.59 336	95.29 123	96.58 104	88.43 111	83.49 326	92.98 255	75.28 206	95.83 353	78.97 307	81.15 370	93.79 311

test11								96.57 105

fmvsm_s_conf0.5_n_2		93.47 66	93.83 57	92.39 146	95.36 147	81.19 207	95.20 135	96.56 106	90.37 37	97.13 15	98.03 27	77.47 175	98.96 83	97.79 5	96.58 118	97.03 155

GDP-MVS		92.04 101	91.46 108	93.75 74	94.55 205	84.69 86	95.60 110	96.56 106	87.83 135	93.07 85	95.89 122	73.44 239	98.65 119	90.22 133	96.03 131	97.91 94

DPM-MVS		92.58 94	91.74 104	95.08 15	96.19 102	89.31 5	92.66 290	96.56 106	83.44 259	91.68 131	95.04 166	86.60 43	98.99 76	85.60 196	97.92 80	96.93 165

balanced_conf03		93.98 52	94.22 43	93.26 87	96.13 105	83.29 135	96.27 48	96.52 109	89.82 55	95.56 41	95.51 142	84.50 75	98.79 106	94.83 42	98.86 19	97.72 108

ETV-MVS		92.74 92	92.66 89	92.97 106	95.20 157	84.04 112	95.07 142	96.51 110	90.73 30	92.96 86	91.19 318	84.06 79	98.34 155	91.72 108	96.54 119	96.54 188

MVSMamba_PlusPlus		93.44 70	93.54 71	93.14 95	96.58 89	83.05 148	96.06 68	96.50 111	84.42 237	94.09 61	95.56 141	85.01 68	98.69 116	94.96 40	98.66 41	97.67 111

CPTT-MVS		91.99 102	91.80 102	92.55 135	98.24 33	81.98 182	96.76 31	96.49 112	81.89 300	90.24 155	96.44 96	78.59 158	98.61 127	89.68 137	97.85 83	97.06 152

VNet		92.24 100	91.91 101	93.24 88	96.59 87	83.43 129	94.84 158	96.44 113	89.19 83	94.08 64	95.90 121	77.85 172	98.17 167	88.90 149	93.38 196	98.13 73

fmvsm_l_conf0.5_n		94.29 36	94.46 31	93.79 72	95.28 151	85.43 72	95.68 99	96.43 114	86.56 171	96.84 22	97.81 35	87.56 32	98.77 108	97.14 13	96.82 112	97.16 146

OpenMVS	83.78 11	88.74 202	87.29 221	93.08 99	92.70 299	85.39 73	96.57 36	96.43 114	78.74 354	80.85 359	96.07 111	69.64 291	99.01 69	78.01 318	96.65 117	94.83 261

sasdasda		93.27 77	92.75 87	94.85 25	95.70 132	87.66 12	96.33 40	96.41 116	90.00 49	94.09 61	94.60 190	82.33 105	98.62 125	92.40 80	92.86 211	98.27 59

canonicalmvs		93.27 77	92.75 87	94.85 25	95.70 132	87.66 12	96.33 40	96.41 116	90.00 49	94.09 61	94.60 190	82.33 105	98.62 125	92.40 80	92.86 211	98.27 59

UA-Net		92.83 89	92.54 92	93.68 77	96.10 110	84.71 85	95.66 102	96.39 118	91.92 10	93.22 80	96.49 94	83.16 91	98.87 93	84.47 216	95.47 143	97.45 123

PEN-MVS		86.80 274	86.27 260	88.40 319	92.32 308	75.71 349	95.18 136	96.38 119	87.97 127	82.82 335	93.15 249	73.39 241	95.92 348	76.15 338	79.03 399	93.59 324

KinetiMVS		91.82 105	91.30 112	93.39 82	94.72 190	83.36 133	95.45 114	96.37 120	90.33 38	92.17 112	96.03 114	72.32 256	98.75 109	87.94 161	96.34 124	98.07 78

114514_t		89.51 173	88.50 188	92.54 136	98.11 38	81.99 181	95.16 138	96.36 121	70.19 429	85.81 251	95.25 155	76.70 183	98.63 124	82.07 257	96.86 111	97.00 159

casdiffmvs_mvg		92.96 88	92.83 86	93.35 83	94.59 199	83.40 131	95.00 146	96.34 122	90.30 41	92.05 115	96.05 112	83.43 85	98.15 169	92.07 94	95.67 137	98.49 30
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MGCFI-Net		93.03 86	92.63 90	94.23 58	95.62 138	85.92 59	96.08 64	96.33 123	89.86 53	93.89 68	94.66 187	82.11 112	98.50 133	92.33 85	92.82 214	98.27 59

TranMVSNet+NR-MVSNet		88.84 198	87.95 204	91.49 194	92.68 300	83.01 151	94.92 151	96.31 124	89.88 52	85.53 260	93.85 227	76.63 185	96.96 288	81.91 261	79.87 391	94.50 277

test_fmvsmconf0.01_n		93.19 81	93.02 82	93.71 76	89.25 401	84.42 100	96.06 68	96.29 125	89.06 86	94.68 51	98.13 6	79.22 150	98.98 80	97.22 12	97.24 100	97.74 106

dcpmvs_2		93.49 65	94.19 47	91.38 199	97.69 59	76.78 332	94.25 200	96.29 125	88.33 113	94.46 53	96.88 73	88.07 25	98.64 122	93.62 56	98.09 72	98.73 19

test12				94.34 53	97.13 75	86.15 50		96.29 125		91.04 144		85.08 63	99.01 69		98.13 70	97.86 97

fmvsm_l_conf0.5_n_a		94.20 42	94.40 33	93.60 78	95.29 150	84.98 79	95.61 107	96.28 128	86.31 177	96.75 24	97.86 33	87.40 33	98.74 112	97.07 15	97.02 105	97.07 151

NormalMVS		93.46 67	93.16 79	94.37 52	98.40 23	86.20 48	96.30 42	96.27 129	91.65 16	92.68 99	96.13 108	77.97 166	98.84 99	90.75 125	98.26 59	98.07 78

Elysia		90.12 150	89.10 168	93.18 91	93.16 275	84.05 110	95.22 130	96.27 129	85.16 215	90.59 149	94.68 183	64.64 345	98.37 150	86.38 185	95.77 134	97.12 148

StellarMVS		90.12 150	89.10 168	93.18 91	93.16 275	84.05 110	95.22 130	96.27 129	85.16 215	90.59 149	94.68 183	64.64 345	98.37 150	86.38 185	95.77 134	97.12 148

baseline		92.39 99	92.29 97	92.69 127	94.46 211	81.77 188	94.14 206	96.27 129	89.22 81	91.88 122	96.00 115	82.35 104	97.99 189	91.05 117	95.27 151	98.30 51

nrg030		91.08 125	90.39 129	93.17 93	93.07 282	86.91 22	96.41 38	96.26 133	88.30 115	88.37 193	94.85 177	82.19 111	97.64 219	91.09 116	82.95 344	94.96 253

无先验							93.28 263	96.26 133	73.95 404				99.05 61	80.56 287		96.59 184

NR-MVSNet		88.58 208	87.47 217	91.93 171	93.04 285	84.16 107	94.77 163	96.25 135	89.05 87	80.04 373	93.29 244	79.02 152	97.05 283	81.71 268	80.05 388	94.59 269

PAPM_NR		91.22 121	90.78 126	92.52 137	97.60 61	81.46 197	94.37 194	96.24 136	86.39 176	87.41 214	94.80 179	82.06 115	98.48 135	82.80 242	95.37 147	97.61 114

casdiffmvs		92.51 95	92.43 94	92.74 123	94.41 216	81.98 182	94.54 177	96.23 137	89.57 68	91.96 119	96.17 106	82.58 101	98.01 187	90.95 121	95.45 145	98.23 65
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HQP_MVS		90.60 141	90.19 134	91.82 181	94.70 193	82.73 160	95.85 86	96.22 138	90.81 25	86.91 223	94.86 175	74.23 222	98.12 170	88.15 156	89.99 256	94.63 266

plane_prior5								96.22 138					98.12 170	88.15 156	89.99 256	94.63 266

PAPR		90.02 156	89.27 166	92.29 156	95.78 128	80.95 218	92.68 289	96.22 138	81.91 296	86.66 231	93.75 232	82.23 109	98.44 145	79.40 305	94.79 160	97.48 121

TAPA-MVS	84.62 6	88.16 219	87.01 229	91.62 189	96.64 85	80.65 226	94.39 190	96.21 141	76.38 378	86.19 244	95.44 145	79.75 140	98.08 182	62.75 425	95.29 149	96.13 204
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Anonymous20231211		86.59 284	85.13 299	90.98 222	96.52 93	81.50 193	96.14 59	96.16 142	73.78 405	83.65 321	92.15 282	63.26 356	97.37 256	82.82 241	81.74 363	94.06 297

test_fmvsmvis_n_1920		93.44 70	93.55 70	93.10 97	93.67 261	84.26 104	95.83 88	96.14 143	89.00 92	92.43 108	97.50 42	83.37 88	98.72 113	96.61 22	97.44 95	96.32 193

LPG-MVS_test		89.45 176	88.90 178	91.12 209	94.47 209	81.49 195	95.30 121	96.14 143	86.73 167	85.45 266	95.16 162	69.89 287	98.10 172	87.70 164	89.23 274	93.77 316

LGP-MVS_train				91.12 209	94.47 209	81.49 195		96.14 143	86.73 167	85.45 266	95.16 162	69.89 287	98.10 172	87.70 164	89.23 274	93.77 316

RRT-MVS		90.85 128	90.70 127	91.30 203	94.25 224	76.83 331	94.85 157	96.13 146	89.04 88	90.23 156	94.88 173	70.15 284	98.72 113	91.86 106	94.88 158	98.34 44

fmvsm_s_conf0.5_n		93.76 59	94.06 53	92.86 113	95.62 138	83.17 139	96.14 59	96.12 147	88.13 123	95.82 37	98.04 26	83.43 85	98.48 135	96.97 19	96.23 126	96.92 166

ACMM	84.12 9	89.14 187	88.48 191	91.12 209	94.65 196	81.22 205	95.31 119	96.12 147	85.31 209	85.92 249	94.34 200	70.19 283	98.06 184	85.65 195	88.86 279	94.08 296
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.5_n_a		93.57 63	93.76 63	93.00 104	95.02 164	83.67 121	96.19 52	96.10 149	87.27 149	95.98 35	98.05 23	83.07 95	98.45 143	96.68 21	95.51 140	96.88 169

MVS_111021_LR		92.47 97	92.29 97	92.98 105	95.99 119	84.43 98	93.08 272	96.09 150	88.20 120	91.12 143	95.72 135	81.33 124	97.76 208	91.74 107	97.37 97	96.75 177

CLD-MVS		89.47 175	88.90 178	91.18 208	94.22 226	82.07 180	92.13 311	96.09 150	87.90 130	85.37 275	92.45 272	74.38 220	97.56 226	87.15 174	90.43 249	93.93 301
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
alignmvs		93.08 85	92.50 93	94.81 32	95.62 138	87.61 15	95.99 74	96.07 152	89.77 62	94.12 60	94.87 174	80.56 129	98.66 117	92.42 79	93.10 207	98.15 71

XVG-OURS		89.40 181	88.70 182	91.52 192	94.06 233	81.46 197	91.27 334	96.07 152	86.14 183	88.89 184	95.77 132	68.73 309	97.26 265	87.39 170	89.96 258	95.83 221

XVG-OURS-SEG-HR		89.95 160	89.45 157	91.47 196	94.00 239	81.21 206	91.87 318	96.06 154	85.78 190	88.55 189	95.73 134	74.67 216	97.27 263	88.71 152	89.64 267	95.91 215

HQP3-MVS								96.04 155							89.77 265

HQP-MVS		89.80 166	89.28 165	91.34 201	94.17 228	81.56 191	94.39 190	96.04 155	88.81 96	85.43 269	93.97 219	73.83 233	97.96 195	87.11 176	89.77 265	94.50 277

test_vis1_n_1920		89.39 182	89.84 146	88.04 333	92.97 289	72.64 385	94.71 168	96.03 157	86.18 181	91.94 121	96.56 93	61.63 366	95.74 359	93.42 59	95.11 153	95.74 225

mamv4		90.92 126	91.78 103	88.33 324	95.67 134	70.75 408	92.92 282	96.02 158	81.90 297	88.11 196	95.34 151	85.88 52	96.97 287	95.22 38	95.01 154	97.26 134

SDMVSNet		90.19 149	89.61 154	91.93 171	96.00 116	83.09 146	92.89 283	95.98 159	88.73 100	86.85 227	95.20 160	72.09 258	97.08 278	88.90 149	89.85 262	95.63 230

PS-MVSNAJss		89.97 158	89.62 153	91.02 217	91.90 322	80.85 222	95.26 127	95.98 159	86.26 179	86.21 243	94.29 204	79.70 142	97.65 217	88.87 151	88.10 290	94.57 271

Vis-MVSNet		91.75 109	91.23 115	93.29 85	95.32 149	83.78 118	96.14 59	95.98 159	89.89 51	90.45 152	96.58 91	75.09 208	98.31 160	84.75 208	96.90 108	97.78 104
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
viewmacassd2359aftdt		91.67 113	91.43 110	92.37 147	93.95 244	81.00 215	93.90 233	95.97 162	87.75 139	91.45 137	96.04 113	79.92 137	97.97 193	89.26 143	94.67 163	98.14 72

viewmanbaseed2359cas		91.78 107	91.58 106	92.37 147	94.32 222	81.07 212	93.76 238	95.96 163	87.26 150	91.50 134	95.88 123	80.92 128	97.97 193	89.70 136	94.92 157	98.07 78

WR-MVS		88.38 212	87.67 212	90.52 238	93.30 272	80.18 239	93.26 264	95.96 163	88.57 108	85.47 265	92.81 261	76.12 190	96.91 292	81.24 274	82.29 354	94.47 282

OMC-MVS		91.23 120	90.62 128	93.08 99	96.27 100	84.07 108	93.52 248	95.93 165	86.95 160	89.51 169	96.13 108	78.50 160	98.35 154	85.84 194	92.90 210	96.83 175

v7n		86.81 273	85.76 283	89.95 268	90.72 374	79.25 274	95.07 142	95.92 166	84.45 236	82.29 340	90.86 331	72.60 252	97.53 228	79.42 304	80.52 384	93.08 348

AdaColmap		89.89 163	89.07 170	92.37 147	97.41 67	83.03 149	94.42 187	95.92 166	82.81 276	86.34 240	94.65 188	73.89 231	99.02 67	80.69 284	95.51 140	95.05 248

cascas		86.43 292	84.98 302	90.80 229	92.10 315	80.92 220	90.24 357	95.91 168	73.10 412	83.57 324	88.39 389	65.15 342	97.46 238	84.90 206	91.43 233	94.03 299

MVSFormer		91.68 112	91.30 112	92.80 116	93.86 246	83.88 115	95.96 77	95.90 169	84.66 233	91.76 128	94.91 171	77.92 169	97.30 259	89.64 138	97.11 101	97.24 136

test_djsdf		89.03 194	88.64 183	90.21 253	90.74 373	79.28 272	95.96 77	95.90 169	84.66 233	85.33 277	92.94 256	74.02 228	97.30 259	89.64 138	88.53 282	94.05 298

fmvsm_s_conf0.1_n_2		93.16 83	93.42 72	92.37 147	94.62 197	81.13 209	95.23 128	95.89 171	90.30 41	96.74 25	98.02 28	76.14 187	98.95 85	97.64 6	96.21 127	97.03 155

ACMP	84.23 8	89.01 196	88.35 192	90.99 220	94.73 188	81.27 202	95.07 142	95.89 171	86.48 172	83.67 320	94.30 203	69.33 296	97.99 189	87.10 178	88.55 281	93.72 321
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PCF-MVS	84.11 10	87.74 230	86.08 268	92.70 126	94.02 235	84.43 98	89.27 379	95.87 173	73.62 407	84.43 298	94.33 201	78.48 162	98.86 95	70.27 381	94.45 173	94.81 262
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CHOSEN 1792x2688		88.84 198	87.69 211	92.30 155	96.14 104	81.42 199	90.01 366	95.86 174	74.52 398	87.41 214	93.94 220	75.46 205	98.36 152	80.36 289	95.53 139	97.12 148

Anonymous20240529		88.09 221	86.59 246	92.58 133	96.53 92	81.92 185	95.99 74	95.84 175	74.11 402	89.06 179	95.21 159	61.44 370	98.81 103	83.67 230	87.47 301	97.01 158

tfpnnormal		84.72 327	83.23 335	89.20 298	92.79 296	80.05 246	94.48 180	95.81 176	82.38 283	81.08 357	91.21 317	69.01 305	96.95 289	61.69 427	80.59 381	90.58 410

MVS_Test		91.31 119	91.11 117	91.93 171	94.37 217	80.14 241	93.46 251	95.80 177	86.46 174	91.35 140	93.77 230	82.21 110	98.09 180	87.57 166	94.95 156	97.55 119

HyFIR lowres test		88.09 221	86.81 234	91.93 171	96.00 116	80.63 227	90.01 366	95.79 178	73.42 409	87.68 210	92.10 287	73.86 232	97.96 195	80.75 283	91.70 230	97.19 140

EI-MVSNet-Vis-set		93.01 87	92.92 84	93.29 85	95.01 165	83.51 128	94.48 180	95.77 179	90.87 23	92.52 105	96.67 83	84.50 75	99.00 74	91.99 99	94.44 174	97.36 126

cdsmvs_eth3d_5k		22.14 431	29.52 434	0.00 450	0.00 473	0.00 475	0.00 461	95.76 180	0.00 468	0.00 469	94.29 204	75.66 203	0.00 469	0.00 468	0.00 467	0.00 465

DTE-MVSNet		86.11 296	85.48 289	87.98 334	91.65 334	74.92 356	94.93 150	95.75 181	87.36 148	82.26 341	93.04 254	72.85 247	95.82 354	74.04 357	77.46 405	93.20 342

fmvsm_s_conf0.1_n		93.46 67	93.66 68	92.85 114	93.75 253	83.13 141	96.02 72	95.74 182	87.68 141	95.89 36	98.17 4	82.78 99	98.46 139	96.71 20	96.17 128	96.98 160

OPM-MVS		90.12 150	89.56 155	91.82 181	93.14 277	83.90 114	94.16 205	95.74 182	88.96 93	87.86 203	95.43 147	72.48 253	97.91 201	88.10 160	90.18 254	93.65 323
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
EI-MVSNet-UG-set		92.74 92	92.62 91	93.12 96	94.86 179	83.20 138	94.40 188	95.74 182	90.71 31	92.05 115	96.60 90	84.00 80	98.99 76	91.55 111	93.63 187	97.17 141

fmvsm_s_conf0.1_n_a		93.19 81	93.26 75	92.97 106	92.49 302	83.62 124	96.02 72	95.72 185	86.78 165	96.04 33	98.19 3	82.30 107	98.43 147	96.38 23	95.42 146	96.86 170

D2MVS		85.90 299	85.09 300	88.35 321	90.79 369	77.42 322	91.83 319	95.70 186	80.77 325	80.08 372	90.02 359	66.74 327	96.37 327	81.88 262	87.97 294	91.26 396

PS-MVSNAJ		91.18 122	90.92 121	91.96 168	95.26 154	82.60 170	92.09 313	95.70 186	86.27 178	91.84 124	92.46 271	79.70 142	98.99 76	89.08 145	95.86 133	94.29 286

旧先验1					96.79 81	81.81 187		95.67 188			96.81 78	86.69 39			97.66 92	96.97 161

MAR-MVS		90.30 146	89.37 161	93.07 101	96.61 86	84.48 94	95.68 99	95.67 188	82.36 284	87.85 204	92.85 257	76.63 185	98.80 104	80.01 294	96.68 116	95.91 215
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
mvs_tets		88.06 223	87.28 222	90.38 249	90.94 362	79.88 253	95.22 130	95.66 190	85.10 218	84.21 308	93.94 220	63.53 353	97.40 252	88.50 154	88.40 287	93.87 306

MVS		87.44 247	86.10 267	91.44 197	92.61 301	83.62 124	92.63 291	95.66 190	67.26 435	81.47 351	92.15 282	77.95 168	98.22 165	79.71 297	95.48 142	92.47 366

jajsoiax		88.24 217	87.50 215	90.48 242	90.89 366	80.14 241	95.31 119	95.65 192	84.97 222	84.24 307	94.02 215	65.31 341	97.42 244	88.56 153	88.52 283	93.89 302

xiu_mvs_v2_base		91.13 123	90.89 123	91.86 177	94.97 170	82.42 172	92.24 306	95.64 193	86.11 186	91.74 130	93.14 250	79.67 145	98.89 91	89.06 146	95.46 144	94.28 287

UniMVSNet_ETH3D		87.53 243	86.37 254	91.00 219	92.44 305	78.96 277	94.74 165	95.61 194	84.07 242	85.36 276	94.52 194	59.78 386	97.34 257	82.93 237	87.88 295	96.71 179

ab-mvs		89.41 179	88.35 192	92.60 131	95.15 161	82.65 168	92.20 309	95.60 195	83.97 244	88.55 189	93.70 234	74.16 226	98.21 166	82.46 247	89.37 270	96.94 164

diffmvs_AUTHOR		91.51 115	91.44 109	91.73 185	93.09 280	80.27 236	92.51 295	95.58 196	87.22 151	91.80 127	95.57 140	79.96 136	97.48 234	92.23 87	94.97 155	97.45 123

新几何1				93.10 97	97.30 71	84.35 103		95.56 197	71.09 425	91.26 141	96.24 100	82.87 98	98.86 95	79.19 306	98.10 71	96.07 209

anonymousdsp		87.84 226	87.09 225	90.12 258	89.13 402	80.54 231	94.67 170	95.55 198	82.05 290	83.82 315	92.12 284	71.47 263	97.15 272	87.15 174	87.80 299	92.67 360

XVG-ACMP-BASELINE		86.00 297	84.84 307	89.45 293	91.20 347	78.00 301	91.70 323	95.55 198	85.05 220	82.97 333	92.25 280	54.49 415	97.48 234	82.93 237	87.45 303	92.89 354

VPNet		88.20 218	87.47 217	90.39 247	93.56 265	79.46 263	94.04 218	95.54 200	88.67 103	86.96 220	94.58 193	69.33 296	97.15 272	84.05 221	80.53 383	94.56 272

h-mvs33		90.80 129	90.15 136	92.75 122	96.01 115	82.66 164	95.43 115	95.53 201	89.80 58	93.08 83	95.64 137	75.77 197	99.00 74	92.07 94	78.05 401	96.60 183

diffmvs		91.37 118	91.23 115	91.77 184	93.09 280	80.27 236	92.36 300	95.52 202	87.03 157	91.40 139	94.93 170	80.08 134	97.44 242	92.13 93	94.56 169	97.61 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
v1192		87.25 256	86.33 256	90.00 267	90.76 372	79.04 276	93.80 236	95.48 203	82.57 280	85.48 264	91.18 320	73.38 242	97.42 244	82.30 250	82.06 356	93.53 326

VortexMVS		88.42 210	88.01 202	89.63 286	93.89 245	78.82 278	93.82 235	95.47 204	86.67 169	84.53 294	91.99 293	72.62 251	96.65 303	89.02 147	84.09 330	93.41 333

xiu_mvs_v1_base_debu		90.64 138	90.05 140	92.40 143	93.97 241	84.46 95	93.32 257	95.46 205	85.17 212	92.25 109	94.03 212	70.59 275	98.57 130	90.97 118	94.67 163	94.18 288

xiu_mvs_v1_base		90.64 138	90.05 140	92.40 143	93.97 241	84.46 95	93.32 257	95.46 205	85.17 212	92.25 109	94.03 212	70.59 275	98.57 130	90.97 118	94.67 163	94.18 288

xiu_mvs_v1_base_debi		90.64 138	90.05 140	92.40 143	93.97 241	84.46 95	93.32 257	95.46 205	85.17 212	92.25 109	94.03 212	70.59 275	98.57 130	90.97 118	94.67 163	94.18 288

v10		87.25 256	86.38 253	89.85 272	91.19 348	79.50 261	94.48 180	95.45 208	83.79 250	83.62 322	91.19 318	75.13 207	97.42 244	81.94 260	80.60 380	92.63 362

F-COLMAP		87.95 224	86.80 235	91.40 198	96.35 99	80.88 221	94.73 166	95.45 208	79.65 338	82.04 346	94.61 189	71.13 265	98.50 133	76.24 337	91.05 241	94.80 263

PLC	84.53 7	89.06 192	88.03 201	92.15 160	97.27 73	82.69 163	94.29 198	95.44 210	79.71 337	84.01 312	94.18 210	76.68 184	98.75 109	77.28 324	93.41 195	95.02 249
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v144192		87.19 262	86.35 255	89.74 278	90.64 376	78.24 296	93.92 229	95.43 211	81.93 295	85.51 262	91.05 327	74.21 224	97.45 239	82.86 239	81.56 364	93.53 326

v1921920		86.97 269	86.06 269	89.69 282	90.53 381	78.11 299	93.80 236	95.43 211	81.90 297	85.33 277	91.05 327	72.66 249	97.41 250	82.05 258	81.80 361	93.53 326

v1144		87.61 239	86.79 236	90.06 262	91.01 357	79.34 268	93.95 226	95.42 213	83.36 263	85.66 256	91.31 316	74.98 210	97.42 244	83.37 231	82.06 356	93.42 332

v8		87.50 246	86.71 238	89.89 270	91.37 342	79.40 265	94.50 179	95.38 214	84.81 228	83.60 323	91.33 313	76.05 191	97.42 244	82.84 240	80.51 385	92.84 356

sss		88.93 197	88.26 198	90.94 224	94.05 234	80.78 224	91.71 322	95.38 214	81.55 312	88.63 188	93.91 224	75.04 209	95.47 371	82.47 246	91.61 231	96.57 186

v1240		86.78 275	85.85 278	89.56 288	90.45 383	77.79 311	93.61 245	95.37 216	81.65 307	85.43 269	91.15 322	71.50 262	97.43 243	81.47 271	82.05 358	93.47 330

testdata				90.49 241	96.40 96	77.89 306		95.37 216	72.51 417	93.63 72	96.69 81	82.08 114	97.65 217	83.08 234	97.39 96	95.94 214

1314		87.51 244	86.57 247	90.34 251	92.42 306	79.74 258	92.63 291	95.35 218	78.35 360	80.14 370	91.62 307	74.05 227	97.15 272	81.05 275	93.53 190	94.12 292

icg_test_0407_2		89.15 186	88.97 173	89.68 285	93.72 254	77.75 314	88.26 396	95.34 219	85.53 200	88.34 194	94.49 195	77.69 173	93.99 395	84.75 208	92.65 216	97.28 130

IMVS_0407		89.85 165	89.51 156	90.88 225	93.72 254	77.75 314	93.07 274	95.34 219	85.53 200	88.34 194	94.49 195	77.69 173	97.60 222	84.75 208	92.65 216	97.28 130

IMVS_0404		87.60 240	86.84 233	89.89 270	93.72 254	77.75 314	88.56 391	95.34 219	85.53 200	79.98 374	94.49 195	66.54 332	94.64 384	84.75 208	92.65 216	97.28 130

IMVS_0403		89.97 158	89.64 152	90.96 223	93.72 254	77.75 314	93.00 277	95.34 219	85.53 200	88.77 186	94.49 195	78.49 161	97.84 204	84.75 208	92.65 216	97.28 130

V42		87.68 231	86.86 231	90.15 256	90.58 378	80.14 241	94.24 202	95.28 223	83.66 252	85.67 255	91.33 313	74.73 214	97.41 250	84.43 217	81.83 360	92.89 354

EPP-MVSNet		91.70 111	91.56 107	92.13 161	95.88 124	80.50 232	97.33 8	95.25 224	86.15 182	89.76 167	95.60 138	83.42 87	98.32 159	87.37 171	93.25 200	97.56 118

UGNet		89.95 160	88.95 175	92.95 108	94.51 207	83.31 134	95.70 98	95.23 225	89.37 74	87.58 211	93.94 220	64.00 350	98.78 107	83.92 223	96.31 125	96.74 178
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
XXY-MVS		87.65 233	86.85 232	90.03 263	92.14 312	80.60 229	93.76 238	95.23 225	82.94 273	84.60 290	94.02 215	74.27 221	95.49 370	81.04 276	83.68 336	94.01 300

API-MVS		90.66 137	90.07 139	92.45 142	96.36 98	84.57 89	96.06 68	95.22 227	82.39 282	89.13 176	94.27 207	80.32 131	98.46 139	80.16 293	96.71 115	94.33 285

MG-MVS		91.77 108	91.70 105	92.00 165	97.08 76	80.03 248	93.60 246	95.18 228	87.85 134	90.89 146	96.47 95	82.06 115	98.36 152	85.07 202	97.04 104	97.62 113

v2v482		87.84 226	87.06 226	90.17 254	90.99 358	79.23 275	94.00 223	95.13 229	84.87 225	85.53 260	92.07 290	74.45 219	97.45 239	84.71 213	81.75 362	93.85 309

test_yl		90.69 134	90.02 143	92.71 124	95.72 130	82.41 174	94.11 209	95.12 230	85.63 195	91.49 135	94.70 181	74.75 212	98.42 148	86.13 189	92.53 223	97.31 127

DCV-MVSNet		90.69 134	90.02 143	92.71 124	95.72 130	82.41 174	94.11 209	95.12 230	85.63 195	91.49 135	94.70 181	74.75 212	98.42 148	86.13 189	92.53 223	97.31 127

Effi-MVS+		91.59 114	91.11 117	93.01 103	94.35 221	83.39 132	94.60 173	95.10 232	87.10 155	90.57 151	93.10 252	81.43 123	98.07 183	89.29 142	94.48 172	97.59 116

Fast-Effi-MVS+		89.41 179	88.64 183	91.71 187	94.74 187	80.81 223	93.54 247	95.10 232	83.11 268	86.82 229	90.67 341	79.74 141	97.75 212	80.51 288	93.55 189	96.57 186

IterMVS-LS		88.36 214	87.91 208	89.70 281	93.80 250	78.29 295	93.73 240	95.08 234	85.73 192	84.75 287	91.90 297	79.88 138	96.92 291	83.83 224	82.51 350	93.89 302
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
reproduce_monomvs		86.37 293	85.87 277	87.87 338	93.66 262	73.71 369	93.44 252	95.02 235	88.61 106	82.64 338	91.94 295	57.88 399	96.68 301	89.96 134	79.71 393	93.22 340

viewmambaseed2359dif		90.04 155	89.78 149	90.83 226	92.85 294	77.92 303	92.23 307	95.01 236	81.90 297	90.20 157	95.45 144	79.64 147	97.34 257	87.52 168	93.17 202	97.23 139

test222					96.55 90	81.70 189	92.22 308	95.01 236	68.36 433	90.20 157	96.14 107	80.26 133			97.80 86	96.05 212

EI-MVSNet		89.10 188	88.86 180	89.80 277	91.84 324	78.30 294	93.70 243	95.01 236	85.73 192	87.15 218	95.28 153	79.87 139	97.21 270	83.81 225	87.36 304	93.88 305

MVSTER		88.84 198	88.29 196	90.51 239	92.95 290	80.44 233	93.73 240	95.01 236	84.66 233	87.15 218	93.12 251	72.79 248	97.21 270	87.86 162	87.36 304	93.87 306

SSM_0407		90.47 144	89.80 148	92.46 140	94.76 184	82.66 164	93.98 225	95.00 240	85.41 205	88.96 181	95.35 149	76.13 188	97.88 203	85.46 199	93.15 204	96.85 171

SSM_0404		90.73 132	90.08 138	92.69 127	95.00 168	83.13 141	94.32 197	95.00 240	85.41 205	89.84 164	95.35 149	76.13 188	97.98 191	85.46 199	94.18 178	96.95 162

GBi-Net		87.26 254	85.98 272	91.08 213	94.01 236	83.10 143	95.14 139	94.94 242	83.57 254	84.37 299	91.64 303	66.59 329	96.34 330	78.23 315	85.36 318	93.79 311

test1		87.26 254	85.98 272	91.08 213	94.01 236	83.10 143	95.14 139	94.94 242	83.57 254	84.37 299	91.64 303	66.59 329	96.34 330	78.23 315	85.36 318	93.79 311

FMVSNet2		87.19 262	85.82 279	91.30 203	94.01 236	83.67 121	94.79 161	94.94 242	83.57 254	83.88 314	92.05 291	66.59 329	96.51 317	77.56 322	85.01 321	93.73 320

FMVSNet1		85.85 301	84.11 321	91.08 213	92.81 295	83.10 143	95.14 139	94.94 242	81.64 308	82.68 336	91.64 303	59.01 394	96.34 330	75.37 344	83.78 333	93.79 311

test_cas_vis1_n_1920		88.83 201	88.85 181	88.78 308	91.15 352	76.72 333	93.85 234	94.93 246	83.23 267	92.81 92	96.00 115	61.17 377	94.45 385	91.67 109	94.84 159	95.17 244

LS3D		87.89 225	86.32 257	92.59 132	96.07 113	82.92 154	95.23 128	94.92 247	75.66 385	82.89 334	95.98 117	72.48 253	99.21 49	68.43 395	95.23 152	95.64 229

eth_miper_zixun_eth		86.50 288	85.77 282	88.68 313	91.94 319	75.81 347	90.47 351	94.89 248	82.05 290	84.05 310	90.46 345	75.96 195	96.77 296	82.76 243	79.36 396	93.46 331

LTVRE_ROB	82.13 13	86.26 295	84.90 305	90.34 251	94.44 213	81.50 193	92.31 305	94.89 248	83.03 270	79.63 380	92.67 265	69.69 290	97.79 206	71.20 374	86.26 313	91.72 383
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
tt0805		86.92 270	85.74 285	90.48 242	92.22 309	79.98 251	95.63 106	94.88 250	83.83 248	84.74 288	92.80 262	57.61 400	97.67 214	85.48 198	84.42 326	93.79 311

UnsupCasMVSNet_eth		80.07 380	78.27 386	85.46 387	85.24 434	72.63 386	88.45 394	94.87 251	82.99 272	71.64 431	88.07 395	56.34 404	91.75 424	73.48 363	63.36 441	92.01 379

pm-mvs1		86.61 282	85.54 287	89.82 274	91.44 337	80.18 239	95.28 125	94.85 252	83.84 247	81.66 349	92.62 267	72.45 255	96.48 319	79.67 298	78.06 400	92.82 357

ACMH	80.38 17	85.36 311	83.68 328	90.39 247	94.45 212	80.63 227	94.73 166	94.85 252	82.09 289	77.24 398	92.65 266	60.01 384	97.58 224	72.25 369	84.87 323	92.96 351
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvs_anonymous		89.37 183	89.32 163	89.51 292	93.47 267	74.22 364	91.65 325	94.83 254	82.91 274	85.45 266	93.79 228	81.23 125	96.36 329	86.47 183	94.09 179	97.94 89

miper_enhance_ethall		86.90 271	86.18 262	89.06 302	91.66 333	77.58 321	90.22 359	94.82 255	79.16 344	84.48 295	89.10 376	79.19 151	96.66 302	84.06 220	82.94 345	92.94 352

miper_ehance_all_eth		87.22 259	86.62 245	89.02 304	92.13 313	77.40 323	90.91 343	94.81 256	81.28 317	84.32 304	90.08 357	79.26 149	96.62 305	83.81 225	82.94 345	93.04 349

FMVSNet3		87.40 249	86.11 266	91.30 203	93.79 252	83.64 123	94.20 204	94.81 256	83.89 246	84.37 299	91.87 298	68.45 312	96.56 313	78.23 315	85.36 318	93.70 322

WTY-MVS		89.60 170	88.92 176	91.67 188	95.47 145	81.15 208	92.38 299	94.78 258	83.11 268	89.06 179	94.32 202	78.67 157	96.61 308	81.57 269	90.89 243	97.24 136

PAPM		86.68 281	85.39 291	90.53 236	93.05 284	79.33 271	89.79 369	94.77 259	78.82 351	81.95 347	93.24 246	76.81 180	97.30 259	66.94 405	93.16 203	94.95 257

FA-MVS(test-final)		89.66 168	88.91 177	91.93 171	94.57 203	80.27 236	91.36 330	94.74 260	84.87 225	89.82 165	92.61 268	74.72 215	98.47 138	83.97 222	93.53 190	97.04 154

sd_testset		88.59 207	87.85 209	90.83 226	96.00 116	80.42 234	92.35 301	94.71 261	88.73 100	86.85 227	95.20 160	67.31 316	96.43 324	79.64 299	89.85 262	95.63 230

c3_l		87.14 264	86.50 251	89.04 303	92.20 310	77.26 324	91.22 337	94.70 262	82.01 293	84.34 303	90.43 346	78.81 154	96.61 308	83.70 229	81.09 371	93.25 338

CDS-MVSNet		89.45 176	88.51 187	92.29 156	93.62 263	83.61 126	93.01 276	94.68 263	81.95 294	87.82 207	93.24 246	78.69 156	96.99 286	80.34 290	93.23 201	96.28 196
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
GeoE		90.05 154	89.43 159	91.90 176	95.16 159	80.37 235	95.80 89	94.65 264	83.90 245	87.55 213	94.75 180	78.18 165	97.62 221	81.28 273	93.63 187	97.71 109

mamba_0408		89.06 192	87.92 206	92.50 138	94.76 184	82.66 164	79.84 448	94.64 265	85.18 210	88.96 181	95.00 167	76.00 193	97.98 191	83.74 227	93.15 204	96.85 171

SSM_04072		88.57 209	87.92 206	90.51 239	94.76 184	82.66 164	79.84 448	94.64 265	85.18 210	88.96 181	95.00 167	76.00 193	92.03 419	83.74 227	93.15 204	96.85 171

1112_ss		88.42 210	87.33 220	91.72 186	94.92 174	80.98 216	92.97 280	94.54 267	78.16 365	83.82 315	93.88 225	78.78 155	97.91 201	79.45 301	89.41 269	96.26 197

viewmsd2359difaftdt		89.43 178	89.05 172	90.56 235	92.89 293	77.00 328	92.81 286	94.52 268	87.03 157	89.77 166	95.79 130	74.67 216	97.51 230	88.97 148	84.98 322	97.17 141

HY-MVS	83.01 12	89.03 194	87.94 205	92.29 156	94.86 179	82.77 156	92.08 314	94.49 269	81.52 313	86.93 221	92.79 263	78.32 164	98.23 163	79.93 295	90.55 247	95.88 218

CANet_DTU		90.26 148	89.41 160	92.81 115	93.46 268	83.01 151	93.48 249	94.47 270	89.43 72	87.76 209	94.23 209	70.54 279	99.03 64	84.97 203	96.39 123	96.38 191

SymmetryMVS		92.81 91	92.31 95	94.32 54	96.15 103	86.20 48	96.30 42	94.43 271	91.65 16	92.68 99	96.13 108	77.97 166	98.84 99	90.75 125	94.72 161	97.92 92

test_fmvs1_n		87.03 268	87.04 228	86.97 363	89.74 396	71.86 392	94.55 176	94.43 271	78.47 357	91.95 120	95.50 143	51.16 425	93.81 399	93.02 67	94.56 169	95.26 241

v148		87.04 267	86.32 257	89.21 297	90.94 362	77.26 324	93.71 242	94.43 271	84.84 227	84.36 302	90.80 335	76.04 192	97.05 283	82.12 254	79.60 394	93.31 335

OurMVSNet-221017-0		85.35 312	84.64 312	87.49 347	90.77 371	72.59 387	94.01 221	94.40 274	84.72 231	79.62 381	93.17 248	61.91 364	96.72 298	81.99 259	81.16 368	93.16 344

MM		95.10 11	94.91 22	95.68 5	96.09 111	88.34 9	96.68 34	94.37 275	95.08 1	94.68 51	97.72 37	82.94 96	99.64 1	97.85 4	98.76 29	99.06 7

Effi-MVS+-dtu		88.65 204	88.35 192	89.54 289	93.33 271	76.39 339	94.47 183	94.36 276	87.70 140	85.43 269	89.56 371	73.45 238	97.26 265	85.57 197	91.28 235	94.97 250

EG-PatchMatch MVS		82.37 353	80.34 359	88.46 318	90.27 385	79.35 267	92.80 288	94.33 277	77.14 373	73.26 425	90.18 353	47.47 434	96.72 298	70.25 382	87.32 306	89.30 420

BP-MVS1		92.48 96	92.07 99	93.72 75	94.50 208	84.39 101	95.90 82	94.30 278	90.39 36	92.67 101	95.94 119	74.46 218	98.65 119	93.14 64	97.35 98	98.13 73

cl____		86.52 287	85.78 280	88.75 310	92.03 317	76.46 337	90.74 345	94.30 278	81.83 303	83.34 329	90.78 336	75.74 202	96.57 311	81.74 266	81.54 365	93.22 340

DIV-MVS_self_test		86.53 286	85.78 280	88.75 310	92.02 318	76.45 338	90.74 345	94.30 278	81.83 303	83.34 329	90.82 334	75.75 200	96.57 311	81.73 267	81.52 366	93.24 339

Test_1112_low_res		87.65 233	86.51 250	91.08 213	94.94 173	79.28 272	91.77 320	94.30 278	76.04 383	83.51 325	92.37 274	77.86 171	97.73 213	78.69 310	89.13 276	96.22 198

pmmvs6		83.42 345	81.60 349	88.87 307	88.01 417	77.87 307	94.96 148	94.24 282	74.67 397	78.80 388	91.09 325	60.17 383	96.49 318	77.06 329	75.40 414	92.23 375

MVP-Stereo		85.97 298	84.86 306	89.32 295	90.92 364	82.19 178	92.11 312	94.19 283	78.76 353	78.77 389	91.63 306	68.38 313	96.56 313	75.01 349	93.95 181	89.20 423
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
TAMVS		89.21 185	88.29 196	91.96 168	93.71 258	82.62 169	93.30 261	94.19 283	82.22 287	87.78 208	93.94 220	78.83 153	96.95 289	77.70 320	92.98 209	96.32 193

LuminaMVS		90.55 142	89.81 147	92.77 118	92.78 297	84.21 105	94.09 213	94.17 285	85.82 188	91.54 133	94.14 211	69.93 285	97.92 200	91.62 110	94.21 177	96.18 201

jason		90.80 129	90.10 137	92.90 110	93.04 285	83.53 127	93.08 272	94.15 286	80.22 329	91.41 138	94.91 171	76.87 179	97.93 199	90.28 132	96.90 108	97.24 136
jason: jason.
BH-untuned		88.60 206	88.13 200	90.01 266	95.24 155	78.50 288	93.29 262	94.15 286	84.75 230	84.46 296	93.40 238	75.76 199	97.40 252	77.59 321	94.52 171	94.12 292

cl22		86.78 275	85.98 272	89.18 299	92.34 307	77.62 320	90.84 344	94.13 288	81.33 316	83.97 313	90.15 354	73.96 229	96.60 310	84.19 219	82.94 345	93.33 334

ACMH+	81.04 14	85.05 319	83.46 331	89.82 274	94.66 195	79.37 266	94.44 185	94.12 289	82.19 288	78.04 392	92.82 260	58.23 397	97.54 227	73.77 361	82.90 348	92.54 363

miper_lstm_enhance		85.27 315	84.59 313	87.31 352	91.28 346	74.63 359	87.69 407	94.09 290	81.20 321	81.36 354	89.85 365	74.97 211	94.30 390	81.03 278	79.84 392	93.01 350

test_fmvs1		87.34 251	87.56 214	86.68 372	90.59 377	71.80 394	94.01 221	94.04 291	78.30 361	91.97 118	95.22 156	56.28 405	93.71 401	92.89 68	94.71 162	94.52 274

Fast-Effi-MVS+-dtu		87.44 247	86.72 237	89.63 286	92.04 316	77.68 319	94.03 219	93.94 292	85.81 189	82.42 339	91.32 315	70.33 281	97.06 281	80.33 291	90.23 253	94.14 291

KD-MVS_self_test		80.20 378	79.24 374	83.07 405	85.64 432	65.29 434	91.01 341	93.93 293	78.71 355	76.32 405	86.40 416	59.20 391	92.93 412	72.59 367	69.35 427	91.00 404

AUN-MVS		87.78 229	86.54 249	91.48 195	94.82 182	81.05 213	93.91 231	93.93 293	83.00 271	86.93 221	93.53 236	69.50 294	97.67 214	86.14 187	77.12 407	95.73 227

TSAR-MVS + GP.		93.66 62	93.41 73	94.41 49	96.59 87	86.78 26	94.40 188	93.93 293	89.77 62	94.21 57	95.59 139	87.35 34	98.61 127	92.72 72	96.15 129	97.83 100

hse-mvs2		89.88 164	89.34 162	91.51 193	94.83 181	81.12 210	93.94 227	93.91 296	89.80 58	93.08 83	93.60 235	75.77 197	97.66 216	92.07 94	77.07 408	95.74 225

VDD-MVS		90.74 131	89.92 145	93.20 90	96.27 100	83.02 150	95.73 96	93.86 297	88.42 112	92.53 104	96.84 75	62.09 362	98.64 122	90.95 121	92.62 221	97.93 91

lupinMVS		90.92 126	90.21 133	93.03 102	93.86 246	83.88 115	92.81 286	93.86 297	79.84 335	91.76 128	94.29 204	77.92 169	98.04 185	90.48 131	97.11 101	97.17 141

CMPMVS	59.16 21	80.52 374	79.20 376	84.48 397	83.98 437	67.63 426	89.95 368	93.84 299	64.79 441	66.81 439	91.14 323	57.93 398	95.17 376	76.25 336	88.10 290	90.65 406
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SSC-MVS3.2		84.60 330	84.19 317	85.85 383	92.74 298	68.07 420	88.15 398	93.81 300	87.42 147	83.76 317	91.07 326	62.91 358	95.73 360	74.56 355	83.24 343	93.75 318

GA-MVS		86.61 282	85.27 296	90.66 231	91.33 345	78.71 281	90.40 352	93.81 300	85.34 208	85.12 279	89.57 370	61.25 373	97.11 277	80.99 279	89.59 268	96.15 202

test_vis1_n		86.56 285	86.49 252	86.78 370	88.51 407	72.69 382	94.68 169	93.78 302	79.55 339	90.70 147	95.31 152	48.75 431	93.28 407	93.15 63	93.99 180	94.38 284

FE-MVS		87.40 249	86.02 270	91.57 191	94.56 204	79.69 259	90.27 353	93.72 303	80.57 326	88.80 185	91.62 307	65.32 340	98.59 129	74.97 350	94.33 176	96.44 189

guyue		91.12 124	90.84 124	91.96 168	94.59 199	80.57 230	94.87 154	93.71 304	88.96 93	91.14 142	95.22 156	73.22 243	97.76 208	92.01 98	93.81 185	97.54 120

IS-MVSNet		91.43 116	91.09 119	92.46 140	95.87 126	81.38 200	96.95 20	93.69 305	89.72 64	89.50 171	95.98 117	78.57 159	97.77 207	83.02 236	96.50 121	98.22 66

MS-PatchMatch		85.05 319	84.16 319	87.73 340	91.42 340	78.51 287	91.25 335	93.53 306	77.50 368	80.15 369	91.58 309	61.99 363	95.51 367	75.69 341	94.35 175	89.16 424

BH-w/o		87.57 242	87.05 227	89.12 300	94.90 177	77.90 305	92.41 297	93.51 307	82.89 275	83.70 319	91.34 312	75.75 200	97.07 280	75.49 342	93.49 192	92.39 370

UnsupCasMVSNet_bld		76.23 402	73.27 406	85.09 393	83.79 438	72.92 378	85.65 423	93.47 308	71.52 422	68.84 437	79.08 442	49.77 427	93.21 408	66.81 409	60.52 445	89.13 426

USDC		82.76 348	81.26 353	87.26 354	91.17 349	74.55 360	89.27 379	93.39 309	78.26 363	75.30 414	92.08 288	54.43 416	96.63 304	71.64 371	85.79 316	90.61 407

mvsmamba		90.33 145	89.69 151	92.25 159	95.17 158	81.64 190	95.27 126	93.36 310	84.88 224	89.51 169	94.27 207	69.29 300	97.42 244	89.34 141	96.12 130	97.68 110

CNLPA		89.07 191	87.98 203	92.34 151	96.87 79	84.78 84	94.08 214	93.24 311	81.41 314	84.46 296	95.13 164	75.57 204	96.62 305	77.21 325	93.84 184	95.61 232

SD_0403		84.71 328	84.65 310	84.92 394	92.95 290	65.95 429	92.07 315	93.23 312	83.82 249	79.03 384	93.73 233	73.90 230	92.91 413	63.02 424	90.05 255	95.89 217

Anonymous20240521		80.44 376	79.21 375	84.11 401	85.75 431	67.89 422	92.86 285	93.23 312	75.61 387	75.59 413	87.47 403	50.03 426	94.33 389	71.14 377	81.21 367	90.12 413

VDDNet		89.56 172	88.49 190	92.76 120	95.07 163	82.09 179	96.30 42	93.19 314	81.05 323	91.88 122	96.86 74	61.16 378	98.33 157	88.43 155	92.49 225	97.84 99

MonoMVSNet		86.89 272	86.55 248	87.92 337	89.46 400	73.75 368	94.12 207	93.10 315	87.82 136	85.10 280	90.76 337	69.59 292	94.94 382	86.47 183	82.50 351	95.07 247

MSDG		84.86 324	83.09 337	90.14 257	93.80 250	80.05 246	89.18 382	93.09 316	78.89 348	78.19 390	91.91 296	65.86 339	97.27 263	68.47 394	88.45 285	93.11 346

CL-MVSNet_self_test		81.74 358	80.53 356	85.36 388	85.96 428	72.45 389	90.25 355	93.07 317	81.24 319	79.85 378	87.29 405	70.93 269	92.52 415	66.95 404	69.23 428	91.11 401

BH-RMVSNet		88.37 213	87.48 216	91.02 217	95.28 151	79.45 264	92.89 283	93.07 317	85.45 204	86.91 223	94.84 178	70.35 280	97.76 208	73.97 358	94.59 168	95.85 219

MVS_0304		94.18 45	93.80 59	95.34 9	94.91 176	87.62 14	95.97 76	93.01 319	92.58 6	94.22 56	97.20 58	80.56 129	99.59 8	97.04 18	98.68 37	98.81 18

ITE_SJBPF				88.24 328	91.88 323	77.05 327		92.92 320	85.54 198	80.13 371	93.30 243	57.29 401	96.20 335	72.46 368	84.71 324	91.49 390

test_fmvs2		83.98 337	84.03 322	83.83 403	87.16 422	67.53 427	93.93 228	92.89 321	77.62 367	86.89 226	93.53 236	47.18 435	92.02 421	90.54 128	86.51 311	91.93 380

ambc				83.06 406	79.99 448	63.51 441	77.47 451	92.86 322		74.34 421	84.45 427	28.74 452	95.06 380	73.06 365	68.89 431	90.61 407

mmtdpeth		85.04 321	84.15 320	87.72 341	93.11 279	75.74 348	94.37 194	92.83 323	84.98 221	89.31 174	86.41 415	61.61 368	97.14 275	92.63 75	62.11 443	90.29 411

TR-MVS		86.78 275	85.76 283	89.82 274	94.37 217	78.41 290	92.47 296	92.83 323	81.11 322	86.36 238	92.40 273	68.73 309	97.48 234	73.75 362	89.85 262	93.57 325

TransMVSNet (Re)		84.43 332	83.06 339	88.54 316	91.72 329	78.44 289	95.18 136	92.82 325	82.73 278	79.67 379	92.12 284	73.49 237	95.96 346	71.10 378	68.73 432	91.21 397

CHOSEN 280x420		85.15 317	83.99 324	88.65 314	92.47 303	78.40 291	79.68 450	92.76 326	74.90 395	81.41 353	89.59 369	69.85 289	95.51 367	79.92 296	95.29 149	92.03 378

MIMVSNet1		79.38 388	77.28 390	85.69 385	86.35 425	73.67 370	91.61 326	92.75 327	78.11 366	72.64 427	88.12 394	48.16 432	91.97 423	60.32 430	77.49 404	91.43 393

PVSNet	78.82 18	85.55 306	84.65 310	88.23 329	94.72 190	71.93 391	87.12 413	92.75 327	78.80 352	84.95 284	90.53 343	64.43 348	96.71 300	74.74 352	93.86 183	96.06 211

pmmvs4		85.43 309	83.86 326	90.16 255	90.02 391	82.97 153	90.27 353	92.67 329	75.93 384	80.73 361	91.74 301	71.05 266	95.73 360	78.85 309	83.46 340	91.78 382

IterMVS-SCA-FT		85.45 308	84.53 315	88.18 330	91.71 330	76.87 330	90.19 361	92.65 330	85.40 207	81.44 352	90.54 342	66.79 325	95.00 381	81.04 276	81.05 372	92.66 361

Baseline_NR-MVSNet		87.07 266	86.63 244	88.40 319	91.44 337	77.87 307	94.23 203	92.57 331	84.12 241	85.74 254	92.08 288	77.25 177	96.04 340	82.29 251	79.94 389	91.30 395

RPSCF		85.07 318	84.27 316	87.48 348	92.91 292	70.62 410	91.69 324	92.46 332	76.20 382	82.67 337	95.22 156	63.94 351	97.29 262	77.51 323	85.80 315	94.53 273

IterMVS		84.88 323	83.98 325	87.60 343	91.44 337	76.03 343	90.18 362	92.41 333	83.24 266	81.06 358	90.42 347	66.60 328	94.28 391	79.46 300	80.98 377	92.48 365
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AstraMVS		90.69 134	90.30 132	91.84 180	93.81 249	79.85 255	94.76 164	92.39 334	88.96 93	91.01 145	95.87 125	70.69 273	97.94 198	92.49 76	92.70 215	97.73 107

WBMVS		84.97 322	84.18 318	87.34 351	94.14 232	71.62 399	90.20 360	92.35 335	81.61 310	84.06 309	90.76 337	61.82 365	96.52 316	78.93 308	83.81 332	93.89 302

KD-MVS_2432*1600		78.50 393	76.02 400	85.93 380	86.22 426	74.47 361	84.80 429	92.33 336	79.29 341	76.98 400	85.92 419	53.81 419	93.97 396	67.39 401	57.42 448	89.36 418

miper_refine_blended		78.50 393	76.02 400	85.93 380	86.22 426	74.47 361	84.80 429	92.33 336	79.29 341	76.98 400	85.92 419	53.81 419	93.97 396	67.39 401	57.42 448	89.36 418

PatchMatch-RL		86.77 278	85.54 287	90.47 245	95.88 124	82.71 162	90.54 350	92.31 338	79.82 336	84.32 304	91.57 311	68.77 308	96.39 326	73.16 364	93.48 194	92.32 373

COLMAP_ROB	80.39 16	83.96 338	82.04 347	89.74 278	95.28 151	79.75 257	94.25 200	92.28 339	75.17 391	78.02 393	93.77 230	58.60 396	97.84 204	65.06 416	85.92 314	91.63 385
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testing91		87.11 265	86.18 262	89.92 269	94.43 214	75.38 354	91.53 327	92.27 340	86.48 172	86.50 232	90.24 349	61.19 376	97.53 228	82.10 255	90.88 244	96.84 174

FMVSNet5		81.52 364	79.60 370	87.27 353	91.17 349	77.95 302	91.49 328	92.26 341	76.87 374	76.16 406	87.91 398	51.67 423	92.34 417	67.74 400	81.16 368	91.52 388

EPNet_dtu		86.49 290	85.94 275	88.14 331	90.24 386	72.82 380	94.11 209	92.20 342	86.66 170	79.42 382	92.36 275	73.52 236	95.81 355	71.26 373	93.66 186	95.80 223
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ppachtmachnet_test		81.84 356	80.07 364	87.15 360	88.46 410	74.43 363	89.04 385	92.16 343	75.33 389	77.75 395	88.99 379	66.20 335	95.37 373	65.12 415	77.60 403	91.65 384

thres200		87.21 260	86.24 261	90.12 258	95.36 147	78.53 286	93.26 264	92.10 344	86.42 175	88.00 202	91.11 324	69.24 301	98.00 188	69.58 389	91.04 242	93.83 310

Anonymous20231206		81.03 370	79.77 368	84.82 395	87.85 420	70.26 412	91.42 329	92.08 345	73.67 406	77.75 395	89.25 374	62.43 361	93.08 410	61.50 428	82.00 359	91.12 400

EPNet		91.79 106	91.02 120	94.10 60	90.10 388	85.25 75	96.03 71	92.05 346	92.83 5	87.39 217	95.78 131	79.39 148	99.01 69	88.13 158	97.48 94	98.05 83
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TDRefinement		79.81 383	77.34 389	87.22 358	79.24 450	75.48 351	93.12 268	92.03 347	76.45 377	75.01 415	91.58 309	49.19 430	96.44 323	70.22 384	69.18 429	89.75 416

DP-MVS		87.25 256	85.36 293	92.90 110	97.65 60	83.24 136	94.81 160	92.00 348	74.99 393	81.92 348	95.00 167	72.66 249	99.05 61	66.92 407	92.33 226	96.40 190

SixPastTwentyTwo		83.91 340	82.90 342	86.92 365	90.99 358	70.67 409	93.48 249	91.99 349	85.54 198	77.62 397	92.11 286	60.59 380	96.87 294	76.05 339	77.75 402	93.20 342

tfpn200view9		87.58 241	86.64 242	90.41 246	95.99 119	78.64 282	94.58 174	91.98 350	86.94 161	88.09 197	91.77 299	69.18 302	98.10 172	70.13 385	91.10 236	94.48 280

thres400		87.62 238	86.64 242	90.57 233	95.99 119	78.64 282	94.58 174	91.98 350	86.94 161	88.09 197	91.77 299	69.18 302	98.10 172	70.13 385	91.10 236	94.96 253

CR-MVSNet		85.35 312	83.76 327	90.12 258	90.58 378	79.34 268	85.24 426	91.96 352	78.27 362	85.55 258	87.87 399	71.03 267	95.61 363	73.96 359	89.36 271	95.40 236

Patchmtry		82.71 349	80.93 355	88.06 332	90.05 390	76.37 340	84.74 431	91.96 352	72.28 420	81.32 355	87.87 399	71.03 267	95.50 369	68.97 391	80.15 387	92.32 373

pmmvs5		84.21 334	82.84 344	88.34 323	88.95 404	76.94 329	92.41 297	91.91 354	75.63 386	80.28 367	91.18 320	64.59 347	95.57 364	77.09 328	83.47 339	92.53 364

test_0402		81.30 368	79.17 377	87.67 342	93.19 274	78.17 297	92.98 279	91.71 355	75.25 390	76.02 410	90.31 348	59.23 390	96.37 327	50.22 446	83.63 337	88.47 431

tpmvs		83.35 347	82.07 346	87.20 359	91.07 355	71.00 406	88.31 395	91.70 356	78.91 346	80.49 366	87.18 408	69.30 299	97.08 278	68.12 399	83.56 338	93.51 329

SCA		86.32 294	85.18 298	89.73 280	92.15 311	76.60 335	91.12 338	91.69 357	83.53 257	85.50 263	88.81 382	66.79 325	96.48 319	76.65 330	90.35 251	96.12 205

mvs5depth		80.98 371	79.15 378	86.45 374	84.57 436	73.29 375	87.79 403	91.67 358	80.52 327	82.20 344	89.72 367	55.14 412	95.93 347	73.93 360	66.83 435	90.12 413

pmmvs-eth3d		80.97 372	78.72 383	87.74 339	84.99 435	79.97 252	90.11 363	91.65 359	75.36 388	73.51 423	86.03 418	59.45 388	93.96 398	75.17 346	72.21 419	89.29 422

test_fmvs3		77.67 397	77.16 393	79.22 419	79.52 449	61.14 444	92.34 302	91.64 360	73.98 403	78.86 385	86.59 412	27.38 455	87.03 443	88.12 159	75.97 412	89.50 417

thres100view900		87.63 236	86.71 238	90.38 249	96.12 106	78.55 285	95.03 145	91.58 361	87.15 153	88.06 200	92.29 278	68.91 306	98.10 172	70.13 385	91.10 236	94.48 280

thres600view7		87.65 233	86.67 241	90.59 232	96.08 112	78.72 279	94.88 153	91.58 361	87.06 156	88.08 199	92.30 277	68.91 306	98.10 172	70.05 388	91.10 236	94.96 253

MDTV_nov1_ep13			83.56 330		91.69 332	69.93 414	87.75 406	91.54 363	78.60 356	84.86 285	88.90 381	69.54 293	96.03 341	70.25 382	88.93 278

tpm cat1		81.96 354	80.27 360	87.01 362	91.09 354	71.02 405	87.38 411	91.53 364	66.25 437	80.17 368	86.35 417	68.22 314	96.15 338	69.16 390	82.29 354	93.86 308

Anonymous202405211		87.68 231	86.13 264	92.31 154	96.66 84	80.74 225	94.87 154	91.49 365	80.47 328	89.46 172	95.44 145	54.72 414	98.23 163	82.19 253	89.89 260	97.97 87

CVMVSNet		84.69 329	84.79 308	84.37 398	91.84 324	64.92 436	93.70 243	91.47 366	66.19 438	86.16 245	95.28 153	67.18 320	93.33 406	80.89 281	90.42 250	94.88 259

tpmrst		85.35 312	84.99 301	86.43 375	90.88 367	67.88 423	88.71 388	91.43 367	80.13 331	86.08 246	88.80 384	73.05 245	96.02 342	82.48 245	83.40 342	95.40 236

EU-MVSNet		81.32 367	80.95 354	82.42 411	88.50 409	63.67 440	93.32 257	91.33 368	64.02 442	80.57 365	92.83 259	61.21 375	92.27 418	76.34 335	80.38 386	91.32 394

PatchmatchNet		85.85 301	84.70 309	89.29 296	91.76 328	75.54 350	88.49 392	91.30 369	81.63 309	85.05 282	88.70 386	71.71 259	96.24 334	74.61 354	89.05 277	96.08 208
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
baseline1		88.10 220	87.28 222	90.57 233	94.96 171	80.07 244	94.27 199	91.29 370	86.74 166	87.41 214	94.00 217	76.77 182	96.20 335	80.77 282	79.31 397	95.44 234

IB-MVS	80.51 15	85.24 316	83.26 334	91.19 207	92.13 313	79.86 254	91.75 321	91.29 370	83.28 265	80.66 363	88.49 388	61.28 372	98.46 139	80.99 279	79.46 395	95.25 242
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
our_test_3		81.93 355	80.46 358	86.33 377	88.46 410	73.48 373	88.46 393	91.11 372	76.46 376	76.69 403	88.25 392	66.89 323	94.36 388	68.75 392	79.08 398	91.14 399

new-patchmatchnet		76.41 401	75.17 403	80.13 417	82.65 443	59.61 448	87.66 408	91.08 373	78.23 364	69.85 435	83.22 431	54.76 413	91.63 426	64.14 420	64.89 439	89.16 424

test20.03		79.95 382	79.08 379	82.55 408	85.79 430	67.74 425	91.09 339	91.08 373	81.23 320	74.48 420	89.96 362	61.63 366	90.15 433	60.08 431	76.38 410	89.76 415

LF4IMVS		80.37 377	79.07 380	84.27 400	86.64 424	69.87 416	89.39 378	91.05 375	76.38 378	74.97 416	90.00 360	47.85 433	94.25 392	74.55 356	80.82 379	88.69 429

CostFormer		85.77 304	84.94 304	88.26 327	91.16 351	72.58 388	89.47 377	91.04 376	76.26 381	86.45 236	89.97 361	70.74 272	96.86 295	82.35 249	87.07 309	95.34 240

LCM-MVSNet-Re		88.30 216	88.32 195	88.27 326	94.71 192	72.41 390	93.15 267	90.98 377	87.77 137	79.25 383	91.96 294	78.35 163	95.75 358	83.04 235	95.62 138	96.65 182

testing99		86.72 279	85.73 286	89.69 282	94.23 225	74.91 357	91.35 331	90.97 378	86.14 183	86.36 238	90.22 350	59.41 389	97.48 234	82.24 252	90.66 246	96.69 181

myMVS_eth3d28		85.80 303	85.26 297	87.42 350	94.73 188	69.92 415	90.60 349	90.95 379	87.21 152	86.06 247	90.04 358	59.47 387	96.02 342	74.89 351	93.35 199	96.33 192

ET-MVSNet_ETH3D		87.51 244	85.91 276	92.32 153	93.70 260	83.93 113	92.33 303	90.94 380	84.16 239	72.09 428	92.52 270	69.90 286	95.85 352	89.20 144	88.36 288	97.17 141

LCM-MVSNet		66.00 414	62.16 419	77.51 424	64.51 464	58.29 450	83.87 435	90.90 381	48.17 453	54.69 450	73.31 448	16.83 464	86.75 444	65.47 412	61.67 444	87.48 436

AllTest		83.42 345	81.39 351	89.52 290	95.01 165	77.79 311	93.12 268	90.89 382	77.41 369	76.12 407	93.34 239	54.08 417	97.51 230	68.31 396	84.27 328	93.26 336

TestCases				89.52 290	95.01 165	77.79 311		90.89 382	77.41 369	76.12 407	93.34 239	54.08 417	97.51 230	68.31 396	84.27 328	93.26 336

Vis-MVSNet (Re-imp)		89.59 171	89.44 158	90.03 263	95.74 129	75.85 346	95.61 107	90.80 384	87.66 143	87.83 206	95.40 148	76.79 181	96.46 322	78.37 311	96.73 114	97.80 102

OpenMVS_ROB	74.94 19	79.51 387	77.03 394	86.93 364	87.00 423	76.23 342	92.33 303	90.74 385	68.93 431	74.52 419	88.23 393	49.58 428	96.62 305	57.64 438	84.29 327	87.94 434

tt0320		80.13 379	77.41 388	88.29 325	90.50 382	78.02 300	93.10 271	90.71 386	66.06 439	76.75 402	86.97 411	49.56 429	95.40 372	71.65 370	71.41 423	91.46 392

testgi		80.94 373	80.20 362	83.18 404	87.96 418	66.29 428	91.28 333	90.70 387	83.70 251	78.12 391	92.84 258	51.37 424	90.82 431	63.34 421	82.46 352	92.43 368

testing11		86.44 291	85.35 294	89.69 282	94.29 223	75.40 353	91.30 332	90.53 388	84.76 229	85.06 281	90.13 355	58.95 395	97.45 239	82.08 256	91.09 240	96.21 200

MDA-MVSNet-bldmvs		78.85 392	76.31 397	86.46 373	89.76 395	73.88 367	88.79 387	90.42 389	79.16 344	59.18 447	88.33 391	60.20 382	94.04 393	62.00 426	68.96 430	91.48 391

tpm2		84.08 336	82.94 340	87.48 348	91.39 341	71.27 400	89.23 381	90.37 390	71.95 421	84.64 289	89.33 373	67.30 317	96.55 315	75.17 346	87.09 308	94.63 266

TinyColmap		79.76 384	77.69 387	85.97 379	91.71 330	73.12 376	89.55 373	90.36 391	75.03 392	72.03 429	90.19 352	46.22 440	96.19 337	63.11 422	81.03 373	88.59 430

Gipuma		57.99 423	54.91 425	67.24 437	88.51 407	65.59 432	52.21 458	90.33 392	43.58 455	42.84 458	51.18 459	20.29 461	85.07 449	34.77 456	70.45 424	51.05 458
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
sc_t1		81.53 363	78.67 384	90.12 258	90.78 370	78.64 282	93.91 231	90.20 393	68.42 432	80.82 360	89.88 363	46.48 437	96.76 297	76.03 340	71.47 422	94.96 253

dmvs_re		84.20 335	83.22 336	87.14 361	91.83 326	77.81 309	90.04 365	90.19 394	84.70 232	81.49 350	89.17 375	64.37 349	91.13 429	71.58 372	85.65 317	92.46 367

PatchT		82.68 350	81.27 352	86.89 367	90.09 389	70.94 407	84.06 433	90.15 395	74.91 394	85.63 257	83.57 430	69.37 295	94.87 383	65.19 413	88.50 284	94.84 260

MIMVSNet		82.59 351	80.53 356	88.76 309	91.51 335	78.32 293	86.57 417	90.13 396	79.32 340	80.70 362	88.69 387	52.98 421	93.07 411	66.03 411	88.86 279	94.90 258

dp		81.47 365	80.23 361	85.17 392	89.92 393	65.49 433	86.74 415	90.10 397	76.30 380	81.10 356	87.12 409	62.81 359	95.92 348	68.13 398	79.88 390	94.09 295

MDA-MVSNet_test_wron		79.21 390	77.19 392	85.29 389	88.22 414	72.77 381	85.87 420	90.06 398	74.34 399	62.62 444	87.56 402	66.14 336	91.99 422	66.90 408	73.01 416	91.10 402

PMMVS		85.71 305	84.96 303	87.95 335	88.90 405	77.09 326	88.68 389	90.06 398	72.32 419	86.47 233	90.76 337	72.15 257	94.40 387	81.78 265	93.49 192	92.36 371

YYNet1		79.22 389	77.20 391	85.28 390	88.20 415	72.66 384	85.87 420	90.05 400	74.33 400	62.70 442	87.61 401	66.09 337	92.03 419	66.94 405	72.97 417	91.15 398

tpm		84.73 326	84.02 323	86.87 368	90.33 384	68.90 418	89.06 384	89.94 401	80.85 324	85.75 253	89.86 364	68.54 311	95.97 345	77.76 319	84.05 331	95.75 224

LFMVS		90.08 153	89.13 167	92.95 108	96.71 82	82.32 176	96.08 64	89.91 402	86.79 164	92.15 114	96.81 78	62.60 360	98.34 155	87.18 173	93.90 182	98.19 67

thisisatest0530		88.67 203	87.61 213	91.86 177	94.87 178	80.07 244	94.63 172	89.90 403	84.00 243	88.46 191	93.78 229	66.88 324	98.46 139	83.30 232	92.65 216	97.06 152

test-LLR		85.87 300	85.41 290	87.25 355	90.95 360	71.67 397	89.55 373	89.88 404	83.41 260	84.54 292	87.95 396	67.25 318	95.11 378	81.82 263	93.37 197	94.97 250

test-mter		84.54 331	83.64 329	87.25 355	90.95 360	71.67 397	89.55 373	89.88 404	79.17 343	84.54 292	87.95 396	55.56 407	95.11 378	81.82 263	93.37 197	94.97 250

tttt0517		88.61 205	87.78 210	91.11 212	94.96 171	77.81 309	95.35 117	89.69 406	85.09 219	88.05 201	94.59 192	66.93 322	98.48 135	83.27 233	92.13 228	97.03 155

PVSNet_0	73.20 20	77.22 398	74.83 404	84.37 398	90.70 375	71.10 403	83.09 438	89.67 407	72.81 416	73.93 422	83.13 432	60.79 379	93.70 402	68.54 393	50.84 453	88.30 432

UBG		85.51 307	84.57 314	88.35 321	94.21 227	71.78 395	90.07 364	89.66 408	82.28 286	85.91 250	89.01 378	61.30 371	97.06 281	76.58 333	92.06 229	96.22 198

testing3-2		86.72 279	86.71 238	86.74 371	96.11 109	65.92 430	93.39 254	89.65 409	89.46 70	87.84 205	92.79 263	59.17 392	97.60 222	81.31 272	90.72 245	96.70 180

JIA-IIPM		81.04 369	78.98 381	87.25 355	88.64 406	73.48 373	81.75 442	89.61 410	73.19 411	82.05 345	73.71 447	66.07 338	95.87 351	71.18 376	84.60 325	92.41 369

thisisatest0515		87.33 252	85.99 271	91.37 200	93.49 266	79.55 260	90.63 348	89.56 411	80.17 330	87.56 212	90.86 331	67.07 321	98.28 161	81.50 270	93.02 208	96.29 195

tt0320-xc		79.63 386	76.66 395	88.52 317	91.03 356	78.72 279	93.00 277	89.53 412	66.37 436	76.11 409	87.11 410	46.36 439	95.32 375	72.78 366	67.67 433	91.51 389

testing222		84.84 325	83.32 332	89.43 294	94.15 231	75.94 344	91.09 339	89.41 413	84.90 223	85.78 252	89.44 372	52.70 422	96.28 333	70.80 380	91.57 232	96.07 209

ADS-MVSNet		81.56 362	79.78 366	86.90 366	91.35 343	71.82 393	83.33 436	89.16 414	72.90 414	82.24 342	85.77 421	64.98 343	93.76 400	64.57 418	83.74 334	95.12 245

baseline2		86.50 288	85.39 291	89.84 273	91.12 353	76.70 334	91.88 317	88.58 415	82.35 285	79.95 375	90.95 329	73.42 240	97.63 220	80.27 292	89.95 259	95.19 243

ADS-MVSNet2		81.66 360	79.71 369	87.50 346	91.35 343	74.19 365	83.33 436	88.48 416	72.90 414	82.24 342	85.77 421	64.98 343	93.20 409	64.57 418	83.74 334	95.12 245

ETVMVS		84.43 332	82.92 341	88.97 306	94.37 217	74.67 358	91.23 336	88.35 417	83.37 262	86.06 247	89.04 377	55.38 409	95.67 362	67.12 403	91.34 234	96.58 185

WB-MVSnew		83.77 342	83.28 333	85.26 391	91.48 336	71.03 404	91.89 316	87.98 418	78.91 346	84.78 286	90.22 350	69.11 304	94.02 394	64.70 417	90.44 248	90.71 405

TESTMET0.1,1		83.74 343	82.85 343	86.42 376	89.96 392	71.21 402	89.55 373	87.88 419	77.41 369	83.37 328	87.31 404	56.71 403	93.65 403	80.62 286	92.85 213	94.40 283

test0.0.03 1		82.41 352	81.69 348	84.59 396	88.23 413	72.89 379	90.24 357	87.83 420	83.41 260	79.86 377	89.78 366	67.25 318	88.99 441	65.18 414	83.42 341	91.90 381

K. test v3		81.59 361	80.15 363	85.91 382	89.89 394	69.42 417	92.57 293	87.71 421	85.56 197	73.44 424	89.71 368	55.58 406	95.52 366	77.17 326	69.76 426	92.78 358

Patchmatch-test		81.37 366	79.30 373	87.58 344	90.92 364	74.16 366	80.99 443	87.68 422	70.52 427	76.63 404	88.81 382	71.21 264	92.76 414	60.01 433	86.93 310	95.83 221

Patchmatch-RL test		81.67 359	79.96 365	86.81 369	85.42 433	71.23 401	82.17 441	87.50 423	78.47 357	77.19 399	82.50 437	70.81 271	93.48 404	82.66 244	72.89 418	95.71 228

Syy-MVS		80.07 380	79.78 366	80.94 415	91.92 320	59.93 447	89.75 371	87.40 424	81.72 305	78.82 386	87.20 406	66.29 334	91.29 427	47.06 448	87.84 297	91.60 386

myMVS_eth3d		79.67 385	78.79 382	82.32 412	91.92 320	64.08 438	89.75 371	87.40 424	81.72 305	78.82 386	87.20 406	45.33 441	91.29 427	59.09 435	87.84 297	91.60 386

MVStest1		72.91 406	69.70 411	82.54 409	78.14 451	73.05 377	88.21 397	86.21 426	60.69 445	64.70 440	90.53 343	46.44 438	85.70 448	58.78 436	53.62 450	88.87 427

UWE-MVS		83.69 344	83.09 337	85.48 386	93.06 283	65.27 435	90.92 342	86.14 427	79.90 334	86.26 242	90.72 340	57.17 402	95.81 355	71.03 379	92.62 221	95.35 239

ANet_high		58.88 421	54.22 426	72.86 427	56.50 467	56.67 452	80.75 444	86.00 428	73.09 413	37.39 459	64.63 455	22.17 459	79.49 457	43.51 451	23.96 461	82.43 443

test_f		71.95 408	70.87 409	75.21 426	74.21 456	59.37 449	85.07 428	85.82 429	65.25 440	70.42 434	83.13 432	23.62 456	82.93 454	78.32 313	71.94 421	83.33 439

ttmdpeth		76.55 400	74.64 405	82.29 413	82.25 444	67.81 424	89.76 370	85.69 430	70.35 428	75.76 411	91.69 302	46.88 436	89.77 435	66.16 410	63.23 442	89.30 420

door-mid								85.49 431

testing3		80.46 375	79.59 371	83.06 406	93.44 269	64.64 437	93.33 256	85.47 432	84.34 238	79.93 376	90.84 333	44.35 443	92.39 416	57.06 440	87.56 300	92.16 377

door								85.33 433

PM-MVS		78.11 395	76.12 399	84.09 402	83.54 439	70.08 413	88.97 386	85.27 434	79.93 333	74.73 418	86.43 414	34.70 451	93.48 404	79.43 303	72.06 420	88.72 428

test1111		89.10 188	88.64 183	90.48 242	95.53 143	74.97 355	96.08 64	84.89 435	88.13 123	90.16 160	96.65 85	63.29 355	98.10 172	86.14 187	96.90 108	98.39 41

FPMVS		64.63 416	62.55 418	70.88 429	70.80 458	56.71 451	84.42 432	84.42 436	51.78 452	49.57 452	81.61 438	23.49 457	81.48 455	40.61 455	76.25 411	74.46 448

ECVR-MVS		89.09 190	88.53 186	90.77 230	95.62 138	75.89 345	96.16 55	84.22 437	87.89 132	90.20 157	96.65 85	63.19 357	98.10 172	85.90 192	96.94 106	98.33 46

pmmvs3		71.81 409	68.71 412	81.11 414	75.86 453	70.42 411	86.74 415	83.66 438	58.95 448	68.64 438	80.89 440	36.93 449	89.52 437	63.10 423	63.59 440	83.39 438

APD_test1		69.04 410	66.26 416	77.36 425	80.51 447	62.79 443	85.46 425	83.51 439	54.11 451	59.14 448	84.79 426	23.40 458	89.61 436	55.22 441	70.24 425	79.68 446

EGC-MVSNET		61.97 417	56.37 422	78.77 421	89.63 398	73.50 372	89.12 383	82.79 440	0.21 467	1.24 468	84.80 425	39.48 446	90.04 434	44.13 450	75.94 413	72.79 449

MVS-HIRNet		73.70 405	72.20 408	78.18 423	91.81 327	56.42 455	82.94 439	82.58 441	55.24 449	68.88 436	66.48 452	55.32 410	95.13 377	58.12 437	88.42 286	83.01 440

new_pmnet		72.15 407	70.13 410	78.20 422	82.95 442	65.68 431	83.91 434	82.40 442	62.94 444	64.47 441	79.82 441	42.85 444	86.26 447	57.41 439	74.44 415	82.65 442

EPMVS		83.90 341	82.70 345	87.51 345	90.23 387	72.67 383	88.62 390	81.96 443	81.37 315	85.01 283	88.34 390	66.31 333	94.45 385	75.30 345	87.12 307	95.43 235

test_method		50.52 426	48.47 428	56.66 441	52.26 468	18.98 472	41.51 460	81.40 444	10.10 462	44.59 457	75.01 446	28.51 453	68.16 459	53.54 443	49.31 454	82.83 441

mvsany_test1		85.42 310	85.30 295	85.77 384	87.95 419	75.41 352	87.61 410	80.97 445	76.82 375	88.68 187	95.83 127	77.44 176	90.82 431	85.90 192	86.51 311	91.08 403

lessismore_v0				86.04 378	88.46 410	68.78 419		80.59 446		73.01 426	90.11 356	55.39 408	96.43 324	75.06 348	65.06 438	92.90 353

DSMNet-mixed		76.94 399	76.29 398	78.89 420	83.10 441	56.11 456	87.78 404	79.77 447	60.65 446	75.64 412	88.71 385	61.56 369	88.34 442	60.07 432	89.29 273	92.21 376

gg-mvs-nofinetune		81.77 357	79.37 372	88.99 305	90.85 368	77.73 318	86.29 418	79.63 448	74.88 396	83.19 332	69.05 451	60.34 381	96.11 339	75.46 343	94.64 167	93.11 346

test_vis1_rt		77.96 396	76.46 396	82.48 410	85.89 429	71.74 396	90.25 355	78.89 449	71.03 426	71.30 432	81.35 439	42.49 445	91.05 430	84.55 215	82.37 353	84.65 437

UWE-MVS-28		78.98 391	78.38 385	80.80 416	88.18 416	60.66 446	90.65 347	78.51 450	78.84 350	77.93 394	90.93 330	59.08 393	89.02 440	50.96 445	90.33 252	92.72 359

mvsany_test3		74.95 403	73.26 407	80.02 418	74.61 454	63.16 442	85.53 424	78.42 451	74.16 401	74.89 417	86.46 413	36.02 450	89.09 439	82.39 248	66.91 434	87.82 435

PMVS	47.18 22	52.22 425	48.46 429	63.48 438	45.72 469	46.20 461	73.41 454	78.31 452	41.03 458	30.06 461	65.68 453	6.05 468	83.43 453	30.04 458	65.86 436	60.80 453
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GG-mvs-BLEND				87.94 336	89.73 397	77.91 304	87.80 402	78.23 453		80.58 364	83.86 428	59.88 385	95.33 374	71.20 374	92.22 227	90.60 409

WB-MVS		67.92 412	67.49 414	69.21 434	81.09 445	41.17 464	88.03 400	78.00 454	73.50 408	62.63 443	83.11 434	63.94 351	86.52 445	25.66 460	51.45 452	79.94 445

dmvs_testset		74.57 404	75.81 402	70.86 430	87.72 421	40.47 465	87.05 414	77.90 455	82.75 277	71.15 433	85.47 423	67.98 315	84.12 452	45.26 449	76.98 409	88.00 433

PMMVS2		59.60 418	56.40 421	69.21 434	68.83 461	46.58 460	73.02 455	77.48 456	55.07 450	49.21 453	72.95 449	17.43 463	80.04 456	49.32 447	44.33 456	80.99 444

SSC-MVS		67.06 413	66.56 415	68.56 436	80.54 446	40.06 466	87.77 405	77.37 457	72.38 418	61.75 445	82.66 436	63.37 354	86.45 446	24.48 461	48.69 455	79.16 447

testf1		59.54 419	56.11 423	69.85 432	69.28 459	56.61 453	80.37 445	76.55 458	42.58 456	45.68 455	75.61 443	11.26 466	84.18 450	43.20 452	60.44 446	68.75 450

APD_test2		59.54 419	56.11 423	69.85 432	69.28 459	56.61 453	80.37 445	76.55 458	42.58 456	45.68 455	75.61 443	11.26 466	84.18 450	43.20 452	60.44 446	68.75 450

test2506		87.21 260	86.28 259	90.02 265	95.62 138	73.64 371	96.25 50	71.38 460	87.89 132	90.45 152	96.65 85	55.29 411	98.09 180	86.03 191	96.94 106	98.33 46

test_vis3_rt		65.12 415	62.60 417	72.69 428	71.44 457	60.71 445	87.17 412	65.55 461	63.80 443	53.22 451	65.65 454	14.54 465	89.44 438	76.65 330	65.38 437	67.91 452

E-PMN		43.23 428	42.29 430	46.03 444	65.58 463	37.41 467	73.51 453	64.62 462	33.99 459	28.47 463	47.87 460	19.90 462	67.91 460	22.23 462	24.45 460	32.77 459

EMVS		42.07 429	41.12 431	44.92 445	63.45 465	35.56 469	73.65 452	63.48 463	33.05 460	26.88 464	45.45 461	21.27 460	67.14 461	19.80 464	23.02 462	32.06 460

MTMP							96.16 55	60.64 464

MVE	39.65 23	43.39 427	38.59 433	57.77 440	56.52 466	48.77 459	55.38 457	58.64 465	29.33 461	28.96 462	52.65 458	4.68 469	64.62 462	28.11 459	33.07 459	59.93 455
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				56.31 442	74.23 455	51.81 458		56.67 466	44.85 454	48.54 454	75.16 445	27.87 454	58.74 464	40.92 454	52.22 451	58.39 456

tmp_tt		35.64 430	39.24 432	24.84 446	14.87 470	23.90 471	62.71 456	51.51 467	6.58 464	36.66 460	62.08 457	44.37 442	30.34 466	52.40 444	22.00 463	20.27 461

kuosan		53.51 424	53.30 427	54.13 443	76.06 452	45.36 462	80.11 447	48.36 468	59.63 447	54.84 449	63.43 456	37.41 448	62.07 463	20.73 463	39.10 458	54.96 457

dongtai		58.82 422	58.24 420	60.56 439	83.13 440	45.09 463	82.32 440	48.22 469	67.61 434	61.70 446	69.15 450	38.75 447	76.05 458	32.01 457	41.31 457	60.55 454

N_pmnet		68.89 411	68.44 413	70.23 431	89.07 403	28.79 470	88.06 399	19.50 470	69.47 430	71.86 430	84.93 424	61.24 374	91.75 424	54.70 442	77.15 406	90.15 412

wuyk23d		21.27 432	20.48 435	23.63 447	68.59 462	36.41 468	49.57 459	6.85 471	9.37 463	7.89 465	4.46 467	4.03 470	31.37 465	17.47 465	16.07 464	3.12 462

testmvs		8.92 433	11.52 436	1.12 449	1.06 471	0.46 474	86.02 419	0.65 472	0.62 465	2.74 466	9.52 465	0.31 472	0.45 468	2.38 466	0.39 465	2.46 464

test123		8.76 434	11.22 437	1.39 448	0.85 472	0.97 473	85.76 422	0.35 473	0.54 466	2.45 467	8.14 466	0.60 471	0.48 467	2.16 467	0.17 466	2.71 463

mmdepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

monomultidepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

test_blank		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet_test		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

DCPMVS		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

pcd_1.5k_mvsjas		6.64 436	8.86 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	79.70 142	0.00 469	0.00 468	0.00 467	0.00 465

sosnet-low-res		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

sosnet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uncertanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

Regformer		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

n2								0.00 474

nn								0.00 474

ab-mvs-re		7.82 435	10.43 438	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	93.88 225	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

WAC-MVS						64.08 438								59.14 434

PC_three_1452									82.47 281	97.09 16	97.07 66	92.72 1	98.04 185	92.70 74	99.02 12	98.86 12

eth-test2					0.00 473

eth-test					0.00 473

OPU-MVS				96.21 3	98.00 44	90.85 3	97.13 15				97.08 64	92.59 2	98.94 86	92.25 86	98.99 14	98.84 15

test_0728_THIRD									90.75 27	97.04 18	98.05 23	92.09 6	99.55 16	95.64 30	99.13 3	99.13 2

GSMVS																96.12 205

test_part2					98.55 12	87.22 19				96.40 26

sam_mvs1												71.70 260				96.12 205

sam_mvs												70.60 274

test_post1							88.00 401				9.81 464	69.31 298	95.53 365	76.65 330

test_post											10.29 463	70.57 278	95.91 350

patchmatchnet-post											83.76 429	71.53 261	96.48 319

gm-plane-assit					89.60 399	68.00 421			77.28 372		88.99 379		97.57 225	79.44 302

test9_res														91.91 103	98.71 32	98.07 78

agg_prior2														90.54 128	98.68 37	98.27 59

test_prior4						85.96 56	94.11 209

test_prior2							94.12 207		87.67 142	92.63 102	96.39 97	86.62 41		91.50 112	98.67 40

旧先验2							93.36 255		71.25 424	94.37 54			97.13 276	86.74 179

新几何2							93.11 270

原ACMM2							92.94 281

testdata2													98.75 109	78.30 314

segment_acmp												87.16 36

testdata1							92.15 310		87.94 128

plane_prior7					94.70 193	82.74 159

plane_prior6					94.52 206	82.75 157						74.23 222

plane_prior4											94.86 175

plane_prior3						82.75 157			90.26 45	86.91 223

plane_prior2							95.85 86		90.81 25

plane_prior1					94.59 199

plane_prior						82.73 160	95.21 133		89.66 66						89.88 261

HQP5-MVS						81.56 191

HQP-NCC					94.17 228		94.39 190		88.81 96	85.43 269

ACMP_Plane					94.17 228		94.39 190		88.81 96	85.43 269

BP-MVS														87.11 176

HQP4-MVS										85.43 269			97.96 195			94.51 276

HQP2-MVS												73.83 233

NP-MVS					94.37 217	82.42 172					93.98 218

MDTV_nov1_ep13_2view						55.91 457	87.62 409		73.32 410	84.59 291		70.33 281		74.65 353		95.50 233

ACMMP++_ref															87.47 301

ACMMP++															88.01 293

Test By Simon												80.02 135

High-resolution multi-view benchmark