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.

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 13	96.44 9	94.41 42

No_MVS				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 13	96.44 9	94.41 42

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 54	82.45 3	96.87 20	83.77 75	96.48 8	94.88 16

MM		89.16 6	89.23 7	88.97 4	90.79 98	73.65 10	92.66 24	91.17 132	86.57 1	87.39 51	94.97 21	71.70 57	97.68 1	92.19 1	95.63 28	95.57 1

HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 28	92.85 60	80.26 11	87.78 42	94.27 41	75.89 19	96.81 23	87.45 41	96.44 9	93.05 120

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 25	93.63 22	74.77 128	92.29 7	95.97 2	74.28 30	97.24 13	88.58 30	96.91 1	94.87 18
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
3Dnovator+	77.84 4	85.48 67	84.47 86	88.51 7	91.08 89	73.49 16	93.18 12	93.78 19	80.79 8	76.66 229	93.37 76	60.40 213	96.75 26	77.20 142	93.73 66	95.29 6

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 65	93.00 47	80.90 7	88.06 37	94.06 52	76.43 16	96.84 21	88.48 33	95.99 18	94.34 48

SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 74	72.96 25	93.73 5	93.67 21	80.19 12	88.10 36	94.80 23	73.76 34	97.11 15	87.51 40	95.82 21	94.90 15
Skip Steuart: Steuart Systems R&D Blog.
MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 17	94.11 7	80.27 10	91.35 14	94.16 47	78.35 13	96.77 24	89.59 15	94.22 62	94.67 29
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
NCCC		88.06 15	88.01 19	88.24 11	94.41 22	73.62 11	91.22 57	92.83 61	81.50 5	85.79 65	93.47 73	73.02 42	97.00 18	84.90 57	94.94 40	94.10 57

ZNCC-MVS		87.94 19	87.85 21	88.20 12	94.39 24	73.33 19	93.03 15	93.81 18	76.81 74	85.24 70	94.32 39	71.76 55	96.93 19	85.53 54	95.79 22	94.32 49

MVS_0304		87.69 21	87.55 26	88.12 13	89.45 134	71.76 53	91.47 52	89.54 185	82.14 3	86.65 59	94.28 40	68.28 103	97.46 6	90.81 6	95.31 34	95.15 8

region2R		87.42 28	87.20 34	88.09 14	94.63 14	73.55 13	93.03 15	93.12 41	76.73 79	84.45 87	94.52 27	69.09 90	96.70 27	84.37 67	94.83 45	94.03 61

ACMMPR		87.44 26	87.23 33	88.08 15	94.64 13	73.59 12	93.04 13	93.20 35	76.78 76	84.66 82	94.52 27	68.81 96	96.65 30	84.53 65	94.90 41	94.00 63

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 46	94.10 9	75.90 98	92.29 7	95.66 10	81.67 6	97.38 11	87.44 42	96.34 15	93.95 66
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
XVS		87.18 34	86.91 41	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 106	94.17 46	67.45 111	96.60 33	83.06 80	94.50 53	94.07 59

X-MVStestdata		80.37 178	77.83 216	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 106	12.47 456	67.45 111	96.60 33	83.06 80	94.50 53	94.07 59

ACMMP_NAP		88.05 17	88.08 18	87.94 19	93.70 41	73.05 22	90.86 60	93.59 24	76.27 92	88.14 35	95.09 19	71.06 67	96.67 29	87.67 38	96.37 14	94.09 58

HFP-MVS		87.58 23	87.47 28	87.94 19	94.58 16	73.54 15	93.04 13	93.24 34	76.78 76	84.91 75	94.44 34	70.78 70	96.61 32	84.53 65	94.89 42	93.66 83

MP-MVS		87.71 20	87.64 23	87.93 21	94.36 26	73.88 6	92.71 23	92.65 71	77.57 49	83.84 102	94.40 36	72.24 49	96.28 43	85.65 52	95.30 35	93.62 90
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTAPA		87.23 33	87.00 36	87.90 22	94.18 35	74.25 5	86.58 212	92.02 98	79.45 22	85.88 63	94.80 23	68.07 104	96.21 46	86.69 46	95.34 32	93.23 106

PGM-MVS		86.68 42	86.27 49	87.90 22	94.22 33	73.38 18	90.22 76	93.04 42	75.53 104	83.86 101	94.42 35	67.87 108	96.64 31	82.70 90	94.57 52	93.66 83

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 61	95.06 1	94.23 3	78.38 38	92.78 4	95.74 6	82.45 3	97.49 4	89.42 17	96.68 2	94.95 12

GST-MVS		87.42 28	87.26 31	87.89 24	94.12 36	72.97 24	92.39 27	93.43 29	76.89 72	84.68 79	93.99 58	70.67 72	96.82 22	84.18 72	95.01 37	93.90 69

SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 68	93.57 8	94.06 11	77.24 60	93.10 1	95.72 8	82.99 1	97.44 7	89.07 22	96.63 4	94.88 16

DeepC-MVS_fast	79.65 3	86.91 38	86.62 44	87.76 27	93.52 46	72.37 43	91.26 54	93.04 42	76.62 82	84.22 93	93.36 77	71.44 61	96.76 25	80.82 105	95.33 33	94.16 54
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 54	93.83 4	93.96 14	75.70 102	91.06 16	96.03 1	76.84 14	97.03 17	89.09 19	95.65 27	94.47 41
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MCST-MVS		87.37 31	87.25 32	87.73 28	94.53 17	72.46 40	89.82 82	93.82 17	73.07 174	84.86 78	92.89 88	76.22 17	96.33 41	84.89 59	95.13 36	94.40 44

TSAR-MVS + MP.		88.02 18	88.11 17	87.72 30	93.68 43	72.13 48	91.41 53	92.35 83	74.62 132	88.90 26	93.85 64	75.75 20	96.00 55	87.80 37	94.63 50	95.04 10
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
mPP-MVS		86.67 43	86.32 47	87.72 30	94.41 22	73.55 13	92.74 21	92.22 89	76.87 73	82.81 118	94.25 43	66.44 122	96.24 45	82.88 85	94.28 60	93.38 99

test_0728_SECOND				87.71 32	95.34 1	71.43 60	93.49 10	94.23 3					97.49 4	89.08 20	96.41 12	94.21 53

DeepC-MVS	79.81 2	87.08 37	86.88 42	87.69 33	91.16 87	72.32 45	90.31 74	93.94 15	77.12 66	82.82 117	94.23 44	72.13 51	97.09 16	84.83 60	95.37 31	93.65 87
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CP-MVS		87.11 35	86.92 40	87.68 34	94.20 34	73.86 7	93.98 3	92.82 64	76.62 82	83.68 105	94.46 31	67.93 106	95.95 58	84.20 71	94.39 57	93.23 106

SF-MVS		88.46 12	88.74 12	87.64 35	92.78 66	71.95 51	92.40 25	94.74 2	75.71 100	89.16 23	95.10 18	75.65 21	96.19 47	87.07 43	96.01 17	94.79 23

MP-MVS-pluss		87.67 22	87.72 22	87.54 36	93.64 44	72.04 50	89.80 84	93.50 26	75.17 117	86.34 61	95.29 17	70.86 69	96.00 55	88.78 28	96.04 16	94.58 34
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
NormalMVS		86.29 50	85.88 59	87.52 37	93.26 52	72.47 38	91.65 43	92.19 92	79.31 24	84.39 89	92.18 102	64.64 143	95.53 67	80.70 108	94.65 48	94.56 37

CANet		86.45 45	86.10 55	87.51 38	90.09 111	70.94 72	89.70 88	92.59 75	81.78 4	81.32 136	91.43 127	70.34 74	97.23 14	84.26 68	93.36 70	94.37 46

HPM-MVS		87.11 35	86.98 38	87.50 39	93.88 39	72.16 47	92.19 34	93.33 32	76.07 95	83.81 103	93.95 61	69.77 82	96.01 54	85.15 55	94.66 47	94.32 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		85.89 60	85.39 70	87.38 40	93.59 45	72.63 33	92.74 21	93.18 40	76.78 76	80.73 148	93.82 65	64.33 145	96.29 42	82.67 91	90.69 109	93.23 106
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
DVP-MVS		89.60 3	90.35 3	87.33 41	95.27 5	71.25 61	93.49 10	92.73 65	77.33 57	92.12 9	95.78 4	80.98 9	97.40 9	89.08 20	96.41 12	93.33 103
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
PHI-MVS		86.43 46	86.17 53	87.24 42	90.88 95	70.96 70	92.27 33	94.07 10	72.45 182	85.22 71	91.90 109	69.47 85	96.42 40	83.28 79	95.94 19	94.35 47

APD-MVS		87.44 26	87.52 27	87.19 43	94.24 32	72.39 41	91.86 41	92.83 61	73.01 176	88.58 28	94.52 27	73.36 35	96.49 38	84.26 68	95.01 37	92.70 132
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CDPH-MVS		85.76 62	85.29 75	87.17 44	93.49 47	71.08 66	88.58 140	92.42 81	68.32 284	84.61 84	93.48 71	72.32 47	96.15 49	79.00 121	95.43 30	94.28 51

train_agg		86.43 46	86.20 50	87.13 45	93.26 52	72.96 25	88.75 131	91.89 106	68.69 277	85.00 73	93.10 81	74.43 27	95.41 76	84.97 56	95.71 25	93.02 122

SymmetryMVS		85.38 72	84.81 80	87.07 46	91.47 83	72.47 38	91.65 43	88.06 242	79.31 24	84.39 89	92.18 102	64.64 143	95.53 67	80.70 108	90.91 106	93.21 109

reproduce-ours		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 120	88.96 24	95.54 12	71.20 65	96.54 36	86.28 48	93.49 67	93.06 118

our_new_method		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 120	88.96 24	95.54 12	71.20 65	96.54 36	86.28 48	93.49 67	93.06 118

CSCG		86.41 48	86.19 52	87.07 46	92.91 63	72.48 37	90.81 61	93.56 25	73.95 148	83.16 112	91.07 139	75.94 18	95.19 85	79.94 116	94.38 58	93.55 94

reproduce_model		87.28 32	87.39 30	86.95 50	93.10 58	71.24 65	91.60 45	93.19 36	74.69 129	88.80 27	95.61 11	70.29 76	96.44 39	86.20 50	93.08 71	93.16 113

SR-MVS		86.73 40	86.67 43	86.91 51	94.11 37	72.11 49	92.37 29	92.56 76	74.50 133	86.84 58	94.65 26	67.31 113	95.77 60	84.80 61	92.85 74	92.84 130

DPM-MVS		84.93 80	84.29 87	86.84 52	90.20 109	73.04 23	87.12 190	93.04 42	69.80 248	82.85 116	91.22 133	73.06 41	96.02 53	76.72 152	94.63 50	91.46 185

TSAR-MVS + GP.		85.71 63	85.33 72	86.84 52	91.34 84	72.50 36	89.07 117	87.28 262	76.41 85	85.80 64	90.22 162	74.15 32	95.37 81	81.82 95	91.88 87	92.65 136

test12				86.80 54	92.63 69	70.70 77		91.79 112		82.71 119		71.67 58	96.16 48		94.50 53	93.54 95

DeepPCF-MVS	80.84 1	88.10 13	88.56 14	86.73 55	92.24 73	69.03 106	89.57 93	93.39 31	77.53 53	89.79 20	94.12 49	78.98 12	96.58 35	85.66 51	95.72 24	94.58 34

SD-MVS		88.06 15	88.50 15	86.71 56	92.60 71	72.71 29	91.81 42	93.19 36	77.87 42	90.32 18	94.00 56	74.83 23	93.78 151	87.63 39	94.27 61	93.65 87
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
3Dnovator	76.31 5	83.38 106	82.31 118	86.59 57	87.94 203	72.94 28	90.64 63	92.14 97	77.21 62	75.47 255	92.83 90	58.56 224	94.72 110	73.24 189	92.71 77	92.13 163

lecture		88.09 14	88.59 13	86.58 58	93.26 52	69.77 92	93.70 6	94.16 5	77.13 65	89.76 21	95.52 14	72.26 48	96.27 44	86.87 44	94.65 48	93.70 82

HPM-MVS_fast		85.35 73	84.95 79	86.57 59	93.69 42	70.58 80	92.15 36	91.62 118	73.89 151	82.67 120	94.09 50	62.60 165	95.54 66	80.93 103	92.93 73	93.57 92

test_prior				86.33 60	92.61 70	69.59 94		92.97 55					95.48 70			93.91 67

MVS_111021_HR		85.14 76	84.75 81	86.32 61	91.65 81	72.70 30	85.98 229	90.33 158	76.11 94	82.08 125	91.61 121	71.36 63	94.17 132	81.02 102	92.58 78	92.08 164

SR-MVS-dyc-post		85.77 61	85.61 66	86.23 62	93.06 60	70.63 78	91.88 39	92.27 85	73.53 162	85.69 66	94.45 32	65.00 141	95.56 64	82.75 86	91.87 88	92.50 142

APD-MVS_3200maxsize		85.97 56	85.88 59	86.22 63	92.69 68	69.53 95	91.93 38	92.99 50	73.54 161	85.94 62	94.51 30	65.80 133	95.61 63	83.04 82	92.51 79	93.53 96

BP-MVS1		84.32 85	83.71 94	86.17 64	87.84 208	67.85 149	89.38 102	89.64 182	77.73 45	83.98 99	92.12 106	56.89 242	95.43 73	84.03 73	91.75 91	95.24 7

GDP-MVS		83.52 101	82.64 112	86.16 65	88.14 192	68.45 128	89.13 114	92.69 66	72.82 180	83.71 104	91.86 112	55.69 249	95.35 82	80.03 114	89.74 127	94.69 28

balanced_conf03		86.78 39	86.99 37	86.15 66	91.24 86	67.61 156	90.51 65	92.90 57	77.26 59	87.44 50	91.63 119	71.27 64	96.06 50	85.62 53	95.01 37	94.78 24

DP-MVS Recon		83.11 114	82.09 122	86.15 66	94.44 19	70.92 73	88.79 128	92.20 91	70.53 226	79.17 170	91.03 142	64.12 147	96.03 51	68.39 244	90.14 118	91.50 181

EPNet		83.72 95	82.92 108	86.14 68	84.22 310	69.48 97	91.05 59	85.27 296	81.30 6	76.83 224	91.65 117	66.09 128	95.56 64	76.00 158	93.85 64	93.38 99
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVSMamba_PlusPlus		85.99 54	85.96 58	86.05 69	91.09 88	67.64 155	89.63 91	92.65 71	72.89 179	84.64 83	91.71 115	71.85 53	96.03 51	84.77 62	94.45 56	94.49 40

sasdasda		85.91 58	85.87 61	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 39	91.23 131	73.28 37	93.91 145	81.50 97	88.80 141	94.77 25

canonicalmvs		85.91 58	85.87 61	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 39	91.23 131	73.28 37	93.91 145	81.50 97	88.80 141	94.77 25

h-mvs33		83.15 111	82.19 119	86.02 72	90.56 101	70.85 75	88.15 157	89.16 207	76.02 96	84.67 80	91.39 128	61.54 186	95.50 69	82.71 88	75.48 340	91.72 175

alignmvs		85.48 67	85.32 73	85.96 73	89.51 130	69.47 98	89.74 86	92.47 77	76.17 93	87.73 46	91.46 126	70.32 75	93.78 151	81.51 96	88.95 138	94.63 33

CS-MVS		86.69 41	86.95 39	85.90 74	90.76 99	67.57 158	92.83 18	93.30 33	79.67 19	84.57 86	92.27 100	71.47 60	95.02 96	84.24 70	93.46 69	95.13 9

DELS-MVS		85.41 70	85.30 74	85.77 75	88.49 177	67.93 147	85.52 247	93.44 28	78.70 34	83.63 108	89.03 194	74.57 24	95.71 62	80.26 113	94.04 63	93.66 83
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
SPE-MVS-test		86.29 50	86.48 45	85.71 76	91.02 91	67.21 173	92.36 30	93.78 19	78.97 33	83.51 109	91.20 134	70.65 73	95.15 87	81.96 94	94.89 42	94.77 25

fmvsm_s_conf0.5_n_9		87.39 30	87.95 20	85.70 77	89.48 133	67.88 148	88.59 139	89.05 212	80.19 12	90.70 17	95.40 15	74.56 25	93.92 144	91.54 2	92.07 85	95.31 5

casdiffmvs_mvg		85.99 54	86.09 56	85.70 77	87.65 219	67.22 172	88.69 135	93.04 42	79.64 21	85.33 69	92.54 97	73.30 36	94.50 118	83.49 76	91.14 101	95.37 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Elysia		81.53 141	80.16 156	85.62 79	85.51 278	68.25 135	88.84 126	92.19 92	71.31 203	80.50 151	89.83 168	46.89 343	94.82 104	76.85 147	89.57 129	93.80 77

StellarMVS		81.53 141	80.16 156	85.62 79	85.51 278	68.25 135	88.84 126	92.19 92	71.31 203	80.50 151	89.83 168	46.89 343	94.82 104	76.85 147	89.57 129	93.80 77

ETV-MVS		84.90 82	84.67 82	85.59 81	89.39 138	68.66 123	88.74 133	92.64 73	79.97 16	84.10 96	85.71 290	69.32 87	95.38 78	80.82 105	91.37 98	92.72 131

test_fmvsmconf_n		85.92 57	86.04 57	85.57 82	85.03 294	69.51 96	89.62 92	90.58 147	73.42 165	87.75 44	94.02 54	72.85 44	93.24 177	90.37 7	90.75 108	93.96 64

test_fmvsmconf0.1_n		85.61 65	85.65 65	85.50 83	82.99 343	69.39 103	89.65 89	90.29 161	73.31 168	87.77 43	94.15 48	71.72 56	93.23 178	90.31 8	90.67 110	93.89 70

UA-Net		85.08 78	84.96 78	85.45 84	92.07 75	68.07 141	89.78 85	90.86 142	82.48 2	84.60 85	93.20 80	69.35 86	95.22 84	71.39 210	90.88 107	93.07 117

Vis-MVSNet		83.46 103	82.80 110	85.43 85	90.25 108	68.74 117	90.30 75	90.13 166	76.33 91	80.87 145	92.89 88	61.00 200	94.20 129	72.45 202	90.97 104	93.35 102
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
KinetiMVS		83.31 109	82.61 113	85.39 86	87.08 242	67.56 159	88.06 159	91.65 116	77.80 44	82.21 123	91.79 113	57.27 237	94.07 135	77.77 136	89.89 125	94.56 37

test_fmvsmconf0.01_n		84.73 83	84.52 85	85.34 87	80.25 385	69.03 106	89.47 95	89.65 181	73.24 172	86.98 56	94.27 41	66.62 118	93.23 178	90.26 9	89.95 123	93.78 79

EI-MVSNet-Vis-set		84.19 86	83.81 92	85.31 88	88.18 189	67.85 149	87.66 173	89.73 179	80.05 15	82.95 113	89.59 179	70.74 71	94.82 104	80.66 110	84.72 208	93.28 105

MAR-MVS		81.84 132	80.70 142	85.27 89	91.32 85	71.53 58	89.82 82	90.92 138	69.77 250	78.50 183	86.21 281	62.36 171	94.52 117	65.36 268	92.05 86	89.77 257
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
Effi-MVS+		83.62 99	83.08 103	85.24 90	88.38 183	67.45 161	88.89 122	89.15 208	75.50 105	82.27 121	88.28 219	69.61 84	94.45 121	77.81 135	87.84 156	93.84 73

MVSFormer		82.85 117	82.05 123	85.24 90	87.35 225	70.21 82	90.50 67	90.38 154	68.55 279	81.32 136	89.47 182	61.68 183	93.46 168	78.98 122	90.26 116	92.05 165

fmvsm_l_conf0.5_n_3		86.02 52	86.32 47	85.14 92	87.20 234	68.54 126	89.57 93	90.44 152	75.31 111	87.49 48	94.39 37	72.86 43	92.72 205	89.04 24	90.56 111	94.16 54

OPM-MVS		83.50 102	82.95 107	85.14 92	88.79 167	70.95 71	89.13 114	91.52 121	77.55 52	80.96 144	91.75 114	60.71 203	94.50 118	79.67 119	86.51 179	89.97 249
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP_MVS		83.64 97	83.14 102	85.14 92	90.08 112	68.71 119	91.25 55	92.44 78	79.12 28	78.92 174	91.00 144	60.42 211	95.38 78	78.71 125	86.32 181	91.33 186

mamba_0404		81.91 130	80.84 141	85.13 95	89.24 147	68.26 133	87.84 170	89.25 202	71.06 212	80.62 149	90.39 155	59.57 216	94.65 114	72.45 202	87.19 167	92.47 145

test_fmvsm_n_1920		85.29 74	85.34 71	85.13 95	86.12 264	69.93 88	88.65 137	90.78 143	69.97 244	88.27 32	93.98 59	71.39 62	91.54 256	88.49 32	90.45 113	93.91 67

EI-MVSNet-UG-set		83.81 91	83.38 99	85.09 97	87.87 206	67.53 160	87.44 181	89.66 180	79.74 18	82.23 122	89.41 188	70.24 77	94.74 109	79.95 115	83.92 223	92.99 125

QAPM		80.88 154	79.50 175	85.03 98	88.01 201	68.97 110	91.59 46	92.00 100	66.63 306	75.15 273	92.16 104	57.70 231	95.45 71	63.52 280	88.76 143	90.66 212

casdiffmvs		85.11 77	85.14 76	85.01 99	87.20 234	65.77 199	87.75 171	92.83 61	77.84 43	84.36 92	92.38 99	72.15 50	93.93 143	81.27 101	90.48 112	95.33 4
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PCF-MVS	73.52 7	80.38 176	78.84 192	85.01 99	87.71 216	68.99 109	83.65 290	91.46 126	63.00 349	77.77 204	90.28 158	66.10 127	95.09 94	61.40 304	88.22 153	90.94 201
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
nrg030		83.88 90	83.53 96	84.96 101	86.77 249	69.28 105	90.46 70	92.67 68	74.79 127	82.95 113	91.33 130	72.70 46	93.09 191	80.79 107	79.28 290	92.50 142

VDD-MVS		83.01 116	82.36 117	84.96 101	91.02 91	66.40 183	88.91 121	88.11 238	77.57 49	84.39 89	93.29 78	52.19 283	93.91 145	77.05 145	88.70 145	94.57 36

PVSNet_Blended_VisFu		82.62 119	81.83 128	84.96 101	90.80 97	69.76 93	88.74 133	91.70 115	69.39 256	78.96 172	88.46 214	65.47 135	94.87 103	74.42 175	88.57 146	90.24 231

CPTT-MVS		83.73 94	83.33 101	84.92 104	93.28 49	70.86 74	92.09 37	90.38 154	68.75 276	79.57 163	92.83 90	60.60 209	93.04 196	80.92 104	91.56 95	90.86 203

EC-MVSNet		86.01 53	86.38 46	84.91 105	89.31 143	66.27 186	92.32 31	93.63 22	79.37 23	84.17 95	91.88 110	69.04 94	95.43 73	83.93 74	93.77 65	93.01 123

mamba_test_0407		81.58 140	80.48 148	84.87 106	88.81 163	67.96 145	87.37 182	89.25 202	71.06 212	79.48 165	90.39 155	59.57 216	94.48 120	72.45 202	85.93 191	92.18 159

OMC-MVS		82.69 118	81.97 126	84.85 107	88.75 169	67.42 162	87.98 161	90.87 141	74.92 123	79.72 161	91.65 117	62.19 175	93.96 137	75.26 168	86.42 180	93.16 113

EIA-MVS		83.31 109	82.80 110	84.82 108	89.59 126	65.59 203	88.21 153	92.68 67	74.66 131	78.96 172	86.42 277	69.06 92	95.26 83	75.54 164	90.09 119	93.62 90

PAPM_NR		83.02 115	82.41 115	84.82 108	92.47 72	66.37 184	87.93 165	91.80 111	73.82 152	77.32 212	90.66 149	67.90 107	94.90 100	70.37 220	89.48 132	93.19 112

baseline		84.93 80	84.98 77	84.80 110	87.30 232	65.39 208	87.30 186	92.88 58	77.62 47	84.04 98	92.26 101	71.81 54	93.96 137	81.31 99	90.30 115	95.03 11

lupinMVS		81.39 146	80.27 154	84.76 111	87.35 225	70.21 82	85.55 243	86.41 280	62.85 352	81.32 136	88.61 209	61.68 183	92.24 228	78.41 129	90.26 116	91.83 168

fmvsm_s_conf0.5_n_8		86.56 44	87.17 35	84.73 112	87.76 215	65.62 202	89.20 107	92.21 90	79.94 17	89.74 22	94.86 22	68.63 98	94.20 129	90.83 5	91.39 97	94.38 45

jason		81.39 146	80.29 153	84.70 113	86.63 254	69.90 90	85.95 230	86.77 275	63.24 345	81.07 142	89.47 182	61.08 199	92.15 230	78.33 130	90.07 121	92.05 165
jason: jason.
ET-MVSNet_ETH3D		78.63 218	76.63 250	84.64 114	86.73 250	69.47 98	85.01 257	84.61 305	69.54 254	66.51 384	86.59 270	50.16 313	91.75 245	76.26 154	84.24 219	92.69 134

EPP-MVSNet		83.40 105	83.02 105	84.57 115	90.13 110	64.47 232	92.32 31	90.73 144	74.45 136	79.35 168	91.10 137	69.05 93	95.12 88	72.78 193	87.22 166	94.13 56

UGNet		80.83 156	79.59 173	84.54 116	88.04 198	68.09 140	89.42 99	88.16 237	76.95 70	76.22 241	89.46 184	49.30 326	93.94 140	68.48 242	90.31 114	91.60 176
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
LPG-MVS_test		82.08 126	81.27 132	84.50 117	89.23 148	68.76 115	90.22 76	91.94 104	75.37 109	76.64 230	91.51 123	54.29 262	94.91 98	78.44 127	83.78 224	89.83 254

LGP-MVS_train				84.50 117	89.23 148	68.76 115		91.94 104	75.37 109	76.64 230	91.51 123	54.29 262	94.91 98	78.44 127	83.78 224	89.83 254

test_fmvsmvis_n_1920		84.02 89	83.87 91	84.49 119	84.12 312	69.37 104	88.15 157	87.96 245	70.01 242	83.95 100	93.23 79	68.80 97	91.51 259	88.61 29	89.96 122	92.57 137

MSLP-MVS++		85.43 69	85.76 63	84.45 120	91.93 77	70.24 81	90.71 62	92.86 59	77.46 55	84.22 93	92.81 92	67.16 115	92.94 198	80.36 111	94.35 59	90.16 233

Effi-MVS+-dtu		80.03 184	78.57 196	84.42 121	85.13 291	68.74 117	88.77 129	88.10 239	74.99 119	74.97 279	83.49 346	57.27 237	93.36 172	73.53 183	80.88 268	91.18 190

HQP-MVS		82.61 120	82.02 124	84.37 122	89.33 140	66.98 176	89.17 109	92.19 92	76.41 85	77.23 215	90.23 161	60.17 214	95.11 90	77.47 139	85.99 189	91.03 196

ACMP	74.13 6	81.51 145	80.57 145	84.36 123	89.42 135	68.69 122	89.97 80	91.50 125	74.46 135	75.04 277	90.41 154	53.82 268	94.54 115	77.56 138	82.91 244	89.86 253
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
原ACMM1				84.35 124	93.01 62	68.79 113		92.44 78	63.96 342	81.09 141	91.57 122	66.06 129	95.45 71	67.19 254	94.82 46	88.81 289

PS-MVSNAJss		82.07 127	81.31 131	84.34 125	86.51 256	67.27 169	89.27 105	91.51 122	71.75 193	79.37 167	90.22 162	63.15 159	94.27 125	77.69 137	82.36 252	91.49 182

thisisatest0530		79.40 198	77.76 221	84.31 126	87.69 218	65.10 217	87.36 183	84.26 312	70.04 240	77.42 209	88.26 221	49.94 317	94.79 108	70.20 222	84.70 209	93.03 121

fmvsm_s_conf0.5_n_4		85.39 71	85.75 64	84.30 127	86.70 251	65.83 195	88.77 129	89.78 175	75.46 106	88.35 30	93.73 67	69.19 89	93.06 193	91.30 3	88.44 150	94.02 62

CLD-MVS		82.31 123	81.65 129	84.29 128	88.47 178	67.73 153	85.81 237	92.35 83	75.78 99	78.33 189	86.58 272	64.01 148	94.35 122	76.05 157	87.48 162	90.79 205
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
fmvsm_s_conf0.1_n_a		83.32 108	82.99 106	84.28 129	83.79 320	68.07 141	89.34 104	82.85 338	69.80 248	87.36 52	94.06 52	68.34 102	91.56 254	87.95 36	83.46 237	93.21 109

fmvsm_s_conf0.5_n_a		83.63 98	83.41 98	84.28 129	86.14 263	68.12 139	89.43 97	82.87 337	70.27 237	87.27 53	93.80 66	69.09 90	91.58 251	88.21 35	83.65 231	93.14 115

fmvsm_l_conf0.5_n		84.47 84	84.54 83	84.27 131	85.42 281	68.81 112	88.49 142	87.26 264	68.08 286	88.03 38	93.49 70	72.04 52	91.77 244	88.90 26	89.14 137	92.24 156

mvsmamba		80.60 169	79.38 177	84.27 131	89.74 124	67.24 171	87.47 178	86.95 270	70.02 241	75.38 261	88.93 199	51.24 300	92.56 211	75.47 166	89.22 135	93.00 124

API-MVS		81.99 129	81.23 133	84.26 133	90.94 93	70.18 87	91.10 58	89.32 196	71.51 200	78.66 179	88.28 219	65.26 136	95.10 93	64.74 274	91.23 100	87.51 321

fmvsm_s_conf0.5_n_5		85.22 75	85.55 67	84.25 134	86.26 258	67.40 164	89.18 108	89.31 197	72.50 181	88.31 31	93.86 63	69.66 83	91.96 236	89.81 11	91.05 102	93.38 99

114514_t		80.68 165	79.51 174	84.20 135	94.09 38	67.27 169	89.64 90	91.11 135	58.75 392	74.08 292	90.72 148	58.10 227	95.04 95	69.70 229	89.42 133	90.30 229

IS-MVSNet		83.15 111	82.81 109	84.18 136	89.94 119	63.30 263	91.59 46	88.46 235	79.04 30	79.49 164	92.16 104	65.10 138	94.28 124	67.71 247	91.86 90	94.95 12

MVS_111021_LR		82.61 120	82.11 120	84.11 137	88.82 162	71.58 57	85.15 253	86.16 286	74.69 129	80.47 153	91.04 140	62.29 172	90.55 287	80.33 112	90.08 120	90.20 232

fmvsm_s_conf0.1_n		83.56 100	83.38 99	84.10 138	84.86 296	67.28 168	89.40 101	83.01 333	70.67 221	87.08 54	93.96 60	68.38 101	91.45 262	88.56 31	84.50 211	93.56 93

FA-MVS(test-final)		80.96 153	79.91 163	84.10 138	88.30 186	65.01 218	84.55 270	90.01 169	73.25 171	79.61 162	87.57 239	58.35 226	94.72 110	71.29 211	86.25 183	92.56 138

Anonymous20240529		80.19 182	78.89 191	84.10 138	90.60 100	64.75 226	88.95 120	90.90 139	65.97 314	80.59 150	91.17 136	49.97 316	93.73 157	69.16 235	82.70 249	93.81 75

RRT-MVS		82.60 122	82.10 121	84.10 138	87.98 202	62.94 274	87.45 180	91.27 128	77.42 56	79.85 159	90.28 158	56.62 245	94.70 112	79.87 117	88.15 154	94.67 29

OpenMVS	72.83 10	79.77 187	78.33 203	84.09 142	85.17 287	69.91 89	90.57 64	90.97 137	66.70 300	72.17 318	91.91 108	54.70 259	93.96 137	61.81 301	90.95 105	88.41 303

FE-MVS		77.78 241	75.68 262	84.08 143	88.09 196	66.00 190	83.13 304	87.79 251	68.42 283	78.01 197	85.23 305	45.50 362	95.12 88	59.11 324	85.83 194	91.11 192

fmvsm_s_conf0.5_n		83.80 92	83.71 94	84.07 144	86.69 252	67.31 167	89.46 96	83.07 332	71.09 210	86.96 57	93.70 68	69.02 95	91.47 261	88.79 27	84.62 210	93.44 98

hse-mvs2		81.72 134	80.94 139	84.07 144	88.72 170	67.68 154	85.87 233	87.26 264	76.02 96	84.67 80	88.22 222	61.54 186	93.48 166	82.71 88	73.44 368	91.06 194

fmvsm_l_conf0.5_n_a		84.13 87	84.16 88	84.06 146	85.38 282	68.40 129	88.34 149	86.85 274	67.48 293	87.48 49	93.40 75	70.89 68	91.61 249	88.38 34	89.22 135	92.16 162

dcpmvs_2		85.63 64	86.15 54	84.06 146	91.71 80	64.94 221	86.47 215	91.87 108	73.63 157	86.60 60	93.02 86	76.57 15	91.87 242	83.36 77	92.15 83	95.35 3

AdaColmap		80.58 172	79.42 176	84.06 146	93.09 59	68.91 111	89.36 103	88.97 218	69.27 260	75.70 251	89.69 173	57.20 239	95.77 60	63.06 285	88.41 151	87.50 322

AUN-MVS		79.21 203	77.60 226	84.05 149	88.71 171	67.61 156	85.84 235	87.26 264	69.08 268	77.23 215	88.14 227	53.20 275	93.47 167	75.50 165	73.45 367	91.06 194

VDDNet		81.52 143	80.67 143	84.05 149	90.44 104	64.13 239	89.73 87	85.91 289	71.11 209	83.18 111	93.48 71	50.54 309	93.49 165	73.40 186	88.25 152	94.54 39

xiu_mvs_v1_base_debu		80.80 160	79.72 169	84.03 151	87.35 225	70.19 84	85.56 240	88.77 224	69.06 269	81.83 127	88.16 223	50.91 303	92.85 201	78.29 131	87.56 159	89.06 274

xiu_mvs_v1_base		80.80 160	79.72 169	84.03 151	87.35 225	70.19 84	85.56 240	88.77 224	69.06 269	81.83 127	88.16 223	50.91 303	92.85 201	78.29 131	87.56 159	89.06 274

xiu_mvs_v1_base_debi		80.80 160	79.72 169	84.03 151	87.35 225	70.19 84	85.56 240	88.77 224	69.06 269	81.83 127	88.16 223	50.91 303	92.85 201	78.29 131	87.56 159	89.06 274

PAPR		81.66 138	80.89 140	83.99 154	90.27 107	64.00 240	86.76 207	91.77 114	68.84 275	77.13 222	89.50 180	67.63 109	94.88 102	67.55 249	88.52 148	93.09 116

XVG-OURS		80.41 174	79.23 183	83.97 155	85.64 274	69.02 108	83.03 309	90.39 153	71.09 210	77.63 206	91.49 125	54.62 261	91.35 265	75.71 160	83.47 236	91.54 179

XVG-OURS-SEG-HR		80.81 157	79.76 168	83.96 156	85.60 276	68.78 114	83.54 296	90.50 150	70.66 224	76.71 228	91.66 116	60.69 204	91.26 268	76.94 146	81.58 260	91.83 168

HyFIR lowres test		77.53 249	75.40 269	83.94 157	89.59 126	66.62 180	80.36 342	88.64 232	56.29 409	76.45 235	85.17 307	57.64 232	93.28 174	61.34 306	83.10 243	91.91 167

tttt0517		79.40 198	77.91 212	83.90 158	88.10 195	63.84 245	88.37 148	84.05 314	71.45 201	76.78 226	89.12 191	49.93 319	94.89 101	70.18 223	83.18 242	92.96 126

LuminaMVS		80.68 165	79.62 172	83.83 159	85.07 293	68.01 144	86.99 195	88.83 221	70.36 232	81.38 135	87.99 230	50.11 314	92.51 215	79.02 120	86.89 173	90.97 199

fmvsm_s_conf0.1_n_2		83.80 92	83.79 93	83.83 159	85.62 275	64.94 221	87.03 193	86.62 278	74.32 138	87.97 41	94.33 38	60.67 205	92.60 208	89.72 12	87.79 157	93.96 64

fmvsm_s_conf0.5_n_2		84.04 88	84.11 89	83.81 161	86.17 262	65.00 219	86.96 196	87.28 262	74.35 137	88.25 33	94.23 44	61.82 181	92.60 208	89.85 10	88.09 155	93.84 73

GeoE		81.71 135	81.01 138	83.80 162	89.51 130	64.45 233	88.97 119	88.73 229	71.27 206	78.63 180	89.76 172	66.32 124	93.20 183	69.89 227	86.02 188	93.74 80

MGCFI-Net		85.06 79	85.51 68	83.70 163	89.42 135	63.01 269	89.43 97	92.62 74	76.43 84	87.53 47	91.34 129	72.82 45	93.42 171	81.28 100	88.74 144	94.66 32

PS-MVSNAJ		81.69 136	81.02 137	83.70 163	89.51 130	68.21 138	84.28 279	90.09 167	70.79 218	81.26 140	85.62 295	63.15 159	94.29 123	75.62 162	88.87 140	88.59 298

fmvsm_s_conf0.5_n_6		85.55 66	86.20 50	83.60 165	87.32 231	65.13 214	88.86 123	91.63 117	75.41 107	88.23 34	93.45 74	68.56 99	92.47 216	89.52 16	92.78 75	93.20 111

xiu_mvs_v2_base		81.69 136	81.05 136	83.60 165	89.15 151	68.03 143	84.46 273	90.02 168	70.67 221	81.30 139	86.53 275	63.17 158	94.19 131	75.60 163	88.54 147	88.57 299

ACMM	73.20 8	80.78 164	79.84 166	83.58 167	89.31 143	68.37 130	89.99 79	91.60 119	70.28 236	77.25 213	89.66 175	53.37 273	93.53 164	74.24 178	82.85 245	88.85 287
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LFMVS		81.82 133	81.23 133	83.57 168	91.89 78	63.43 261	89.84 81	81.85 349	77.04 69	83.21 110	93.10 81	52.26 282	93.43 170	71.98 205	89.95 123	93.85 71

Fast-Effi-MVS+		80.81 157	79.92 162	83.47 169	88.85 159	64.51 229	85.53 245	89.39 190	70.79 218	78.49 184	85.06 310	67.54 110	93.58 159	67.03 257	86.58 177	92.32 151

CHOSEN 1792x2688		77.63 248	75.69 261	83.44 170	89.98 118	68.58 125	78.70 366	87.50 258	56.38 408	75.80 250	86.84 258	58.67 223	91.40 264	61.58 303	85.75 195	90.34 226

新几何1				83.42 171	93.13 56	70.71 76		85.48 295	57.43 403	81.80 130	91.98 107	63.28 153	92.27 226	64.60 275	92.99 72	87.27 328

DP-MVS		76.78 263	74.57 281	83.42 171	93.29 48	69.46 100	88.55 141	83.70 318	63.98 341	70.20 336	88.89 201	54.01 267	94.80 107	46.66 407	81.88 258	86.01 356

MVS_Test		83.15 111	83.06 104	83.41 173	86.86 245	63.21 265	86.11 227	92.00 100	74.31 139	82.87 115	89.44 187	70.03 78	93.21 180	77.39 141	88.50 149	93.81 75

LS3D		76.95 260	74.82 278	83.37 174	90.45 103	67.36 166	89.15 113	86.94 271	61.87 365	69.52 348	90.61 150	51.71 296	94.53 116	46.38 410	86.71 176	88.21 307

IB-MVS	68.01 15	75.85 280	73.36 300	83.31 175	84.76 299	66.03 188	83.38 298	85.06 300	70.21 239	69.40 349	81.05 376	45.76 358	94.66 113	65.10 271	75.49 339	89.25 271
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
MG-MVS		83.41 104	83.45 97	83.28 176	92.74 67	62.28 283	88.17 155	89.50 187	75.22 112	81.49 134	92.74 96	66.75 116	95.11 90	72.85 192	91.58 94	92.45 146

jajsoiax		79.29 201	77.96 210	83.27 177	84.68 301	66.57 182	89.25 106	90.16 165	69.20 265	75.46 257	89.49 181	45.75 359	93.13 189	76.84 149	80.80 270	90.11 237

test_djsdf		80.30 179	79.32 180	83.27 177	83.98 316	65.37 209	90.50 67	90.38 154	68.55 279	76.19 242	88.70 205	56.44 246	93.46 168	78.98 122	80.14 280	90.97 199

test_yl		81.17 148	80.47 149	83.24 179	89.13 152	63.62 248	86.21 224	89.95 171	72.43 185	81.78 131	89.61 177	57.50 234	93.58 159	70.75 215	86.90 171	92.52 140

DCV-MVSNet		81.17 148	80.47 149	83.24 179	89.13 152	63.62 248	86.21 224	89.95 171	72.43 185	81.78 131	89.61 177	57.50 234	93.58 159	70.75 215	86.90 171	92.52 140

mvs_tets		79.13 205	77.77 220	83.22 181	84.70 300	66.37 184	89.17 109	90.19 164	69.38 257	75.40 260	89.46 184	44.17 371	93.15 187	76.78 151	80.70 272	90.14 234

thisisatest0515		77.33 253	75.38 270	83.18 182	85.27 286	63.80 246	82.11 316	83.27 326	65.06 324	75.91 247	83.84 335	49.54 321	94.27 125	67.24 253	86.19 184	91.48 183

CDS-MVSNet		79.07 207	77.70 223	83.17 183	87.60 220	68.23 137	84.40 277	86.20 285	67.49 292	76.36 238	86.54 274	61.54 186	90.79 282	61.86 300	87.33 164	90.49 220
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v7n		78.97 210	77.58 227	83.14 184	83.45 328	65.51 204	88.32 150	91.21 130	73.69 156	72.41 314	86.32 280	57.93 228	93.81 150	69.18 234	75.65 336	90.11 237

BH-RMVSNet		79.61 189	78.44 199	83.14 184	89.38 139	65.93 192	84.95 259	87.15 267	73.56 160	78.19 192	89.79 171	56.67 244	93.36 172	59.53 320	86.74 175	90.13 235

fmvsm_s_conf0.5_n_3		86.36 49	87.46 29	83.09 186	87.08 242	65.21 211	89.09 116	90.21 163	79.67 19	89.98 19	95.02 20	73.17 39	91.71 248	91.30 3	91.60 92	92.34 149

UniMVSNet (Re)		81.60 139	81.11 135	83.09 186	88.38 183	64.41 234	87.60 174	93.02 46	78.42 37	78.56 182	88.16 223	69.78 81	93.26 176	69.58 231	76.49 322	91.60 176

PLC	70.83 11	78.05 234	76.37 256	83.08 188	91.88 79	67.80 151	88.19 154	89.46 188	64.33 334	69.87 345	88.38 216	53.66 269	93.58 159	58.86 327	82.73 247	87.86 313
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v1192		79.59 191	78.43 200	83.07 189	83.55 326	64.52 228	86.93 199	90.58 147	70.83 217	77.78 203	85.90 286	59.15 220	93.94 140	73.96 180	77.19 312	90.76 207

v2v482		80.23 180	79.29 181	83.05 190	83.62 324	64.14 238	87.04 192	89.97 170	73.61 158	78.18 193	87.22 250	61.10 198	93.82 149	76.11 155	76.78 319	91.18 190

TAMVS		78.89 213	77.51 229	83.03 191	87.80 210	67.79 152	84.72 263	85.05 301	67.63 289	76.75 227	87.70 235	62.25 173	90.82 281	58.53 331	87.13 168	90.49 220

v1144		80.03 184	79.03 187	83.01 192	83.78 321	64.51 229	87.11 191	90.57 149	71.96 192	78.08 196	86.20 282	61.41 190	93.94 140	74.93 170	77.23 310	90.60 215

cascas		76.72 264	74.64 280	82.99 193	85.78 271	65.88 194	82.33 313	89.21 205	60.85 371	72.74 308	81.02 377	47.28 339	93.75 155	67.48 250	85.02 203	89.34 269

anonymousdsp		78.60 219	77.15 235	82.98 194	80.51 383	67.08 174	87.24 188	89.53 186	65.66 317	75.16 272	87.19 252	52.52 277	92.25 227	77.17 143	79.34 289	89.61 261

v10		79.74 188	78.67 193	82.97 195	84.06 314	64.95 220	87.88 168	90.62 146	73.11 173	75.11 274	86.56 273	61.46 189	94.05 136	73.68 181	75.55 338	89.90 251

UniMVSNet_NR-MVSNet		81.88 131	81.54 130	82.92 196	88.46 179	63.46 259	87.13 189	92.37 82	80.19 12	78.38 187	89.14 190	71.66 59	93.05 194	70.05 224	76.46 323	92.25 154

DU-MVS		81.12 151	80.52 147	82.90 197	87.80 210	63.46 259	87.02 194	91.87 108	79.01 31	78.38 187	89.07 192	65.02 139	93.05 194	70.05 224	76.46 323	92.20 157

PVSNet_Blended		80.98 152	80.34 151	82.90 197	88.85 159	65.40 206	84.43 275	92.00 100	67.62 290	78.11 194	85.05 311	66.02 130	94.27 125	71.52 207	89.50 131	89.01 279

icg_test_0403		80.80 160	80.12 159	82.87 199	87.13 237	63.59 252	85.19 250	89.33 192	70.51 227	78.49 184	89.03 194	63.26 155	93.27 175	72.56 198	85.56 197	91.74 171

CANet_DTU		80.61 167	79.87 165	82.83 200	85.60 276	63.17 268	87.36 183	88.65 231	76.37 89	75.88 248	88.44 215	53.51 271	93.07 192	73.30 187	89.74 127	92.25 154

V42		79.38 200	78.24 205	82.83 200	81.10 377	65.50 205	85.55 243	89.82 174	71.57 199	78.21 191	86.12 284	60.66 206	93.18 186	75.64 161	75.46 342	89.81 256

Anonymous20231211		78.97 210	77.69 224	82.81 202	90.54 102	64.29 236	90.11 78	91.51 122	65.01 326	76.16 246	88.13 228	50.56 308	93.03 197	69.68 230	77.56 309	91.11 192

AstraMVS		80.81 157	80.14 158	82.80 203	86.05 267	63.96 241	86.46 216	85.90 290	73.71 155	80.85 146	90.56 151	54.06 266	91.57 253	79.72 118	83.97 222	92.86 128

v1921920		79.22 202	78.03 209	82.80 203	83.30 331	63.94 243	86.80 203	90.33 158	69.91 246	77.48 208	85.53 297	58.44 225	93.75 155	73.60 182	76.85 317	90.71 211

v8		79.97 186	79.02 188	82.80 203	84.09 313	64.50 231	87.96 162	90.29 161	74.13 146	75.24 270	86.81 259	62.88 164	93.89 148	74.39 176	75.40 345	90.00 245

TAPA-MVS	73.13 9	79.15 204	77.94 211	82.79 206	89.59 126	62.99 273	88.16 156	91.51 122	65.77 315	77.14 221	91.09 138	60.91 201	93.21 180	50.26 388	87.05 169	92.17 161
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
v144192		79.47 194	78.37 201	82.78 207	83.35 329	63.96 241	86.96 196	90.36 157	69.99 243	77.50 207	85.67 293	60.66 206	93.77 153	74.27 177	76.58 320	90.62 213

NR-MVSNet		80.23 180	79.38 177	82.78 207	87.80 210	63.34 262	86.31 221	91.09 136	79.01 31	72.17 318	89.07 192	67.20 114	92.81 204	66.08 263	75.65 336	92.20 157

diffmvs		82.10 125	81.88 127	82.76 209	83.00 341	63.78 247	83.68 289	89.76 177	72.94 177	82.02 126	89.85 167	65.96 132	90.79 282	82.38 92	87.30 165	93.71 81
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
icg_test_0407		80.61 167	79.90 164	82.75 210	87.13 237	63.59 252	85.33 249	89.33 192	70.51 227	77.82 200	89.03 194	61.84 179	92.91 199	72.56 198	85.56 197	91.74 171

v1240		78.99 209	77.78 219	82.64 211	83.21 333	63.54 256	86.62 211	90.30 160	69.74 253	77.33 211	85.68 292	57.04 240	93.76 154	73.13 190	76.92 314	90.62 213

Fast-Effi-MVS+-dtu		78.02 235	76.49 251	82.62 212	83.16 337	66.96 178	86.94 198	87.45 260	72.45 182	71.49 326	84.17 330	54.79 258	91.58 251	67.61 248	80.31 277	89.30 270

guyue		81.13 150	80.64 144	82.60 213	86.52 255	63.92 244	86.69 209	87.73 253	73.97 147	80.83 147	89.69 173	56.70 243	91.33 267	78.26 134	85.40 201	92.54 139

RPMNet		73.51 309	70.49 332	82.58 214	81.32 375	65.19 212	75.92 391	92.27 85	57.60 401	72.73 309	76.45 416	52.30 281	95.43 73	48.14 402	77.71 305	87.11 334

F-COLMAP		76.38 273	74.33 287	82.50 215	89.28 145	66.95 179	88.41 144	89.03 213	64.05 339	66.83 376	88.61 209	46.78 345	92.89 200	57.48 340	78.55 294	87.67 316

TranMVSNet+NR-MVSNet		80.84 155	80.31 152	82.42 216	87.85 207	62.33 281	87.74 172	91.33 127	80.55 9	77.99 198	89.86 166	65.23 137	92.62 206	67.05 256	75.24 350	92.30 152

MVSTER		79.01 208	77.88 215	82.38 217	83.07 338	64.80 225	84.08 284	88.95 219	69.01 272	78.69 177	87.17 253	54.70 259	92.43 218	74.69 171	80.57 274	89.89 252

PVSNet_BlendedMVS		80.60 169	80.02 160	82.36 218	88.85 159	65.40 206	86.16 226	92.00 100	69.34 258	78.11 194	86.09 285	66.02 130	94.27 125	71.52 207	82.06 255	87.39 323

viewmamba		80.41 174	79.84 166	82.12 219	82.95 345	62.50 279	83.39 297	88.06 242	67.11 295	80.98 143	90.31 157	66.20 126	91.01 278	74.62 172	84.90 205	92.86 128

EI-MVSNet		80.52 173	79.98 161	82.12 219	84.28 308	63.19 267	86.41 217	88.95 219	74.18 144	78.69 177	87.54 242	66.62 118	92.43 218	72.57 196	80.57 274	90.74 209

IterMVS-LS		80.06 183	79.38 177	82.11 221	85.89 268	63.20 266	86.79 204	89.34 191	74.19 143	75.45 258	86.72 262	66.62 118	92.39 220	72.58 195	76.86 316	90.75 208
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
BH-untuned		79.47 194	78.60 195	82.05 222	89.19 150	65.91 193	86.07 228	88.52 234	72.18 187	75.42 259	87.69 236	61.15 197	93.54 163	60.38 312	86.83 174	86.70 344

ACMH+	68.96 14	76.01 278	74.01 289	82.03 223	88.60 174	65.31 210	88.86 123	87.55 256	70.25 238	67.75 363	87.47 244	41.27 389	93.19 185	58.37 333	75.94 333	87.60 318

Anonymous202405211		78.25 226	77.01 237	81.99 224	91.03 90	60.67 304	84.77 262	83.90 316	70.65 225	80.00 158	91.20 134	41.08 391	91.43 263	65.21 269	85.26 202	93.85 71

GA-MVS		76.87 261	75.17 275	81.97 225	82.75 348	62.58 277	81.44 325	86.35 283	72.16 189	74.74 282	82.89 357	46.20 353	92.02 234	68.85 239	81.09 265	91.30 188

CNLPA		78.08 232	76.79 244	81.97 225	90.40 105	71.07 67	87.59 175	84.55 306	66.03 313	72.38 315	89.64 176	57.56 233	86.04 352	59.61 319	83.35 238	88.79 290

MVS		78.19 230	76.99 239	81.78 227	85.66 273	66.99 175	84.66 265	90.47 151	55.08 413	72.02 320	85.27 303	63.83 150	94.11 134	66.10 262	89.80 126	84.24 383

ACMH	67.68 16	75.89 279	73.93 291	81.77 228	88.71 171	66.61 181	88.62 138	89.01 215	69.81 247	66.78 377	86.70 266	41.95 387	91.51 259	55.64 356	78.14 301	87.17 330
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UniMVSNet_ETH3D		79.10 206	78.24 205	81.70 229	86.85 246	60.24 311	87.28 187	88.79 223	74.25 142	76.84 223	90.53 153	49.48 322	91.56 254	67.98 245	82.15 253	93.29 104

VNet		82.21 124	82.41 115	81.62 230	90.82 96	60.93 299	84.47 271	89.78 175	76.36 90	84.07 97	91.88 110	64.71 142	90.26 289	70.68 217	88.89 139	93.66 83

XVG-ACMP-BASELINE		76.11 276	74.27 288	81.62 230	83.20 334	64.67 227	83.60 293	89.75 178	69.75 251	71.85 321	87.09 255	32.78 421	92.11 231	69.99 226	80.43 276	88.09 309

eth_miper_zixun_eth		77.92 238	76.69 248	81.61 232	83.00 341	61.98 286	83.15 303	89.20 206	69.52 255	74.86 281	84.35 324	61.76 182	92.56 211	71.50 209	72.89 372	90.28 230

PAPM		77.68 246	76.40 255	81.51 233	87.29 233	61.85 288	83.78 286	89.59 184	64.74 328	71.23 328	88.70 205	62.59 166	93.66 158	52.66 372	87.03 170	89.01 279

v148		78.72 216	77.80 218	81.47 234	82.73 349	61.96 287	86.30 222	88.08 240	73.26 170	76.18 243	85.47 299	62.46 169	92.36 222	71.92 206	73.82 364	90.09 239

tt0805		78.73 215	77.83 216	81.43 235	85.17 287	60.30 310	89.41 100	90.90 139	71.21 207	77.17 220	88.73 204	46.38 348	93.21 180	72.57 196	78.96 292	90.79 205

LTVRE_ROB	69.57 13	76.25 274	74.54 283	81.41 236	88.60 174	64.38 235	79.24 356	89.12 211	70.76 220	69.79 347	87.86 232	49.09 329	93.20 183	56.21 355	80.16 278	86.65 345
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
GBi-Net		78.40 223	77.40 230	81.40 237	87.60 220	63.01 269	88.39 145	89.28 198	71.63 195	75.34 263	87.28 246	54.80 255	91.11 271	62.72 287	79.57 284	90.09 239

test1		78.40 223	77.40 230	81.40 237	87.60 220	63.01 269	88.39 145	89.28 198	71.63 195	75.34 263	87.28 246	54.80 255	91.11 271	62.72 287	79.57 284	90.09 239

FMVSNet1		77.44 250	76.12 258	81.40 237	86.81 248	63.01 269	88.39 145	89.28 198	70.49 231	74.39 289	87.28 246	49.06 330	91.11 271	60.91 308	78.52 295	90.09 239

baseline2		75.70 281	73.83 294	81.30 240	83.26 332	61.79 290	82.57 312	80.65 361	66.81 297	66.88 375	83.42 347	57.86 230	92.19 229	63.47 281	79.57 284	89.91 250

fmvsm_s_conf0.5_n_7		83.34 107	84.03 90	81.28 241	85.73 272	65.13 214	85.40 248	89.90 173	74.96 122	82.13 124	93.89 62	66.65 117	87.92 331	86.56 47	91.05 102	90.80 204

c3_l		78.75 214	77.91 212	81.26 242	82.89 346	61.56 292	84.09 283	89.13 210	69.97 244	75.56 253	84.29 325	66.36 123	92.09 232	73.47 185	75.48 340	90.12 236

cl22		78.07 233	77.01 237	81.23 243	82.37 358	61.83 289	83.55 294	87.98 244	68.96 273	75.06 276	83.87 333	61.40 191	91.88 241	73.53 183	76.39 325	89.98 248

FMVSNet2		78.20 229	77.21 234	81.20 244	87.60 220	62.89 275	87.47 178	89.02 214	71.63 195	75.29 269	87.28 246	54.80 255	91.10 274	62.38 292	79.38 288	89.61 261

TR-MVS		77.44 250	76.18 257	81.20 244	88.24 187	63.24 264	84.61 268	86.40 281	67.55 291	77.81 202	86.48 276	54.10 264	93.15 187	57.75 339	82.72 248	87.20 329

ab-mvs		79.51 192	78.97 189	81.14 246	88.46 179	60.91 300	83.84 285	89.24 204	70.36 232	79.03 171	88.87 202	63.23 157	90.21 291	65.12 270	82.57 250	92.28 153

MVP-Stereo		76.12 275	74.46 285	81.13 247	85.37 283	69.79 91	84.42 276	87.95 246	65.03 325	67.46 367	85.33 302	53.28 274	91.73 247	58.01 337	83.27 240	81.85 409
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
miper_ehance_all_eth		78.59 220	77.76 221	81.08 248	82.66 351	61.56 292	83.65 290	89.15 208	68.87 274	75.55 254	83.79 337	66.49 121	92.03 233	73.25 188	76.39 325	89.64 260

FIs		82.07 127	82.42 114	81.04 249	88.80 166	58.34 328	88.26 152	93.49 27	76.93 71	78.47 186	91.04 140	69.92 80	92.34 224	69.87 228	84.97 204	92.44 147

SDMVSNet		80.38 176	80.18 155	80.99 250	89.03 157	64.94 221	80.45 341	89.40 189	75.19 115	76.61 232	89.98 164	60.61 208	87.69 335	76.83 150	83.55 233	90.33 227

patch_mono-2		83.65 96	84.54 83	80.99 250	90.06 116	65.83 195	84.21 280	88.74 228	71.60 198	85.01 72	92.44 98	74.51 26	83.50 376	82.15 93	92.15 83	93.64 89

FMVSNet3		77.88 239	76.85 242	80.97 252	86.84 247	62.36 280	86.52 214	88.77 224	71.13 208	75.34 263	86.66 268	54.07 265	91.10 274	62.72 287	79.57 284	89.45 265

miper_enhance_ethall		77.87 240	76.86 241	80.92 253	81.65 365	61.38 294	82.68 310	88.98 216	65.52 319	75.47 255	82.30 366	65.76 134	92.00 235	72.95 191	76.39 325	89.39 267

BH-w/o		78.21 228	77.33 233	80.84 254	88.81 163	65.13 214	84.87 260	87.85 250	69.75 251	74.52 287	84.74 317	61.34 192	93.11 190	58.24 335	85.84 193	84.27 382

COLMAP_ROB	66.92 17	73.01 319	70.41 334	80.81 255	87.13 237	65.63 201	88.30 151	84.19 313	62.96 350	63.80 404	87.69 236	38.04 407	92.56 211	46.66 407	74.91 353	84.24 383
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VPA-MVSNet		80.60 169	80.55 146	80.76 256	88.07 197	60.80 302	86.86 201	91.58 120	75.67 103	80.24 155	89.45 186	63.34 152	90.25 290	70.51 219	79.22 291	91.23 189

EG-PatchMatch MVS		74.04 302	71.82 316	80.71 257	84.92 295	67.42 162	85.86 234	88.08 240	66.04 312	64.22 399	83.85 334	35.10 417	92.56 211	57.44 341	80.83 269	82.16 408

ECVR-MVS		79.61 189	79.26 182	80.67 258	90.08 112	54.69 382	87.89 167	77.44 395	74.88 124	80.27 154	92.79 93	48.96 332	92.45 217	68.55 241	92.50 80	94.86 19

VortexMVS		78.57 221	77.89 214	80.59 259	85.89 268	62.76 276	85.61 238	89.62 183	72.06 190	74.99 278	85.38 301	55.94 248	90.77 284	74.99 169	76.58 320	88.23 305

cl____		77.72 243	76.76 245	80.58 260	82.49 355	60.48 307	83.09 305	87.87 248	69.22 263	74.38 290	85.22 306	62.10 176	91.53 257	71.09 212	75.41 344	89.73 259

DIV-MVS_self_test		77.72 243	76.76 245	80.58 260	82.48 356	60.48 307	83.09 305	87.86 249	69.22 263	74.38 290	85.24 304	62.10 176	91.53 257	71.09 212	75.40 345	89.74 258

MSDG		73.36 313	70.99 327	80.49 262	84.51 306	65.80 197	80.71 336	86.13 287	65.70 316	65.46 390	83.74 338	44.60 366	90.91 280	51.13 381	76.89 315	84.74 378

pmmvs4		74.03 304	71.91 315	80.39 263	81.96 361	68.32 131	81.45 324	82.14 344	59.32 384	69.87 345	85.13 308	52.40 280	88.13 329	60.21 314	74.74 355	84.73 379

HY-MVS	69.67 12	77.95 237	77.15 235	80.36 264	87.57 224	60.21 312	83.37 299	87.78 252	66.11 310	75.37 262	87.06 257	63.27 154	90.48 288	61.38 305	82.43 251	90.40 224

mvs_anonymous		79.42 197	79.11 186	80.34 265	84.45 307	57.97 334	82.59 311	87.62 255	67.40 294	76.17 245	88.56 212	68.47 100	89.59 302	70.65 218	86.05 187	93.47 97

1112_ss		77.40 252	76.43 253	80.32 266	89.11 156	60.41 309	83.65 290	87.72 254	62.13 362	73.05 305	86.72 262	62.58 167	89.97 295	62.11 298	80.80 270	90.59 216

WR-MVS		79.49 193	79.22 184	80.27 267	88.79 167	58.35 327	85.06 256	88.61 233	78.56 35	77.65 205	88.34 217	63.81 151	90.66 286	64.98 272	77.22 311	91.80 170

sc_t1		72.19 328	69.51 339	80.23 268	84.81 297	61.09 297	84.68 264	80.22 371	60.70 372	71.27 327	83.58 344	36.59 412	89.24 309	60.41 311	63.31 412	90.37 225

1314		76.53 266	75.30 273	80.21 269	83.93 317	62.32 282	84.66 265	88.81 222	60.23 376	70.16 339	84.07 332	55.30 252	90.73 285	67.37 251	83.21 241	87.59 320

test1111		79.43 196	79.18 185	80.15 270	89.99 117	53.31 395	87.33 185	77.05 399	75.04 118	80.23 156	92.77 95	48.97 331	92.33 225	68.87 238	92.40 82	94.81 22

IterMVS-SCA-FT		75.43 286	73.87 293	80.11 271	82.69 350	64.85 224	81.57 322	83.47 323	69.16 266	70.49 333	84.15 331	51.95 290	88.15 328	69.23 233	72.14 378	87.34 325

FC-MVSNet-test		81.52 143	82.02 124	80.03 272	88.42 182	55.97 367	87.95 163	93.42 30	77.10 67	77.38 210	90.98 146	69.96 79	91.79 243	68.46 243	84.50 211	92.33 150

testdata				79.97 273	90.90 94	64.21 237		84.71 303	59.27 385	85.40 68	92.91 87	62.02 178	89.08 313	68.95 237	91.37 98	86.63 346

SCA		74.22 299	72.33 312	79.91 274	84.05 315	62.17 284	79.96 349	79.29 381	66.30 309	72.38 315	80.13 389	51.95 290	88.60 323	59.25 322	77.67 308	88.96 283

thres400		76.50 267	75.37 271	79.86 275	89.13 152	57.65 341	85.17 251	83.60 319	73.41 166	76.45 235	86.39 278	52.12 284	91.95 237	48.33 398	83.75 227	90.00 245

test_0402		72.79 322	70.44 333	79.84 276	88.13 193	65.99 191	85.93 231	84.29 310	65.57 318	67.40 370	85.49 298	46.92 342	92.61 207	35.88 435	74.38 358	80.94 414

OurMVSNet-221017-0		74.26 298	72.42 311	79.80 277	83.76 322	59.59 318	85.92 232	86.64 276	66.39 308	66.96 374	87.58 238	39.46 397	91.60 250	65.76 266	69.27 392	88.22 306

test2506		77.30 254	76.49 251	79.74 278	90.08 112	52.02 399	87.86 169	63.10 442	74.88 124	80.16 157	92.79 93	38.29 406	92.35 223	68.74 240	92.50 80	94.86 19

SixPastTwentyTwo		73.37 311	71.26 325	79.70 279	85.08 292	57.89 336	85.57 239	83.56 321	71.03 214	65.66 389	85.88 287	42.10 385	92.57 210	59.11 324	63.34 411	88.65 296

thres600view7		76.50 267	75.44 267	79.68 280	89.40 137	57.16 347	85.53 245	83.23 327	73.79 153	76.26 240	87.09 255	51.89 292	91.89 240	48.05 403	83.72 230	90.00 245

CR-MVSNet		73.37 311	71.27 324	79.67 281	81.32 375	65.19 212	75.92 391	80.30 369	59.92 379	72.73 309	81.19 374	52.50 278	86.69 343	59.84 316	77.71 305	87.11 334

D2MVS		74.82 293	73.21 301	79.64 282	79.81 392	62.56 278	80.34 343	87.35 261	64.37 333	68.86 354	82.66 361	46.37 349	90.10 292	67.91 246	81.24 263	86.25 349

AllTest		70.96 337	68.09 352	79.58 283	85.15 289	63.62 248	84.58 269	79.83 374	62.31 359	60.32 416	86.73 260	32.02 422	88.96 317	50.28 386	71.57 382	86.15 352

TestCases				79.58 283	85.15 289	63.62 248		79.83 374	62.31 359	60.32 416	86.73 260	32.02 422	88.96 317	50.28 386	71.57 382	86.15 352

tfpn200view9		76.42 271	75.37 271	79.55 285	89.13 152	57.65 341	85.17 251	83.60 319	73.41 166	76.45 235	86.39 278	52.12 284	91.95 237	48.33 398	83.75 227	89.07 272

ICG_test_0404		77.16 256	76.42 254	79.37 286	87.13 237	63.59 252	77.12 385	89.33 192	70.51 227	66.22 387	89.03 194	50.36 311	82.78 381	72.56 198	85.56 197	91.74 171

thres100view900		76.50 267	75.55 266	79.33 287	89.52 129	56.99 350	85.83 236	83.23 327	73.94 149	76.32 239	87.12 254	51.89 292	91.95 237	48.33 398	83.75 227	89.07 272

CostFormer		75.24 290	73.90 292	79.27 288	82.65 352	58.27 329	80.80 331	82.73 340	61.57 366	75.33 267	83.13 352	55.52 250	91.07 277	64.98 272	78.34 300	88.45 301

Test_1112_low_res		76.40 272	75.44 267	79.27 288	89.28 145	58.09 330	81.69 320	87.07 268	59.53 383	72.48 313	86.67 267	61.30 193	89.33 306	60.81 310	80.15 279	90.41 223

K. test v3		71.19 334	68.51 346	79.21 290	83.04 340	57.78 340	84.35 278	76.91 400	72.90 178	62.99 407	82.86 358	39.27 398	91.09 276	61.65 302	52.66 433	88.75 292

testing91		76.54 265	75.66 264	79.18 291	88.43 181	55.89 368	81.08 328	83.00 334	73.76 154	75.34 263	84.29 325	46.20 353	90.07 293	64.33 276	84.50 211	91.58 178

testing99		76.09 277	75.12 276	79.00 292	88.16 190	55.50 374	80.79 332	81.40 354	73.30 169	75.17 271	84.27 328	44.48 368	90.02 294	64.28 277	84.22 220	91.48 183

lessismore_v0				78.97 293	81.01 378	57.15 348		65.99 435		61.16 413	82.82 359	39.12 400	91.34 266	59.67 318	46.92 440	88.43 302

pm-mvs1		77.25 255	76.68 249	78.93 294	84.22 310	58.62 325	86.41 217	88.36 236	71.37 202	73.31 301	88.01 229	61.22 196	89.15 312	64.24 278	73.01 371	89.03 278

icg_test_0407_2		78.92 212	78.93 190	78.90 295	87.13 237	63.59 252	76.58 387	89.33 192	70.51 227	77.82 200	89.03 194	61.84 179	81.38 391	72.56 198	85.56 197	91.74 171

thres200		75.55 283	74.47 284	78.82 296	87.78 213	57.85 337	83.07 307	83.51 322	72.44 184	75.84 249	84.42 320	52.08 287	91.75 245	47.41 405	83.64 232	86.86 340

VPNet		78.69 217	78.66 194	78.76 297	88.31 185	55.72 371	84.45 274	86.63 277	76.79 75	78.26 190	90.55 152	59.30 219	89.70 301	66.63 258	77.05 313	90.88 202

tpm2		73.26 315	71.46 320	78.63 298	83.34 330	56.71 355	80.65 337	80.40 368	56.63 407	73.55 299	82.02 371	51.80 294	91.24 269	56.35 354	78.42 298	87.95 310

pmmvs6		74.69 294	73.39 298	78.61 299	81.38 372	57.48 344	86.64 210	87.95 246	64.99 327	70.18 337	86.61 269	50.43 310	89.52 303	62.12 297	70.18 389	88.83 288

sd_testset		77.70 245	77.40 230	78.60 300	89.03 157	60.02 313	79.00 361	85.83 291	75.19 115	76.61 232	89.98 164	54.81 254	85.46 360	62.63 291	83.55 233	90.33 227

MonoMVSNet		76.49 270	75.80 259	78.58 301	81.55 368	58.45 326	86.36 220	86.22 284	74.87 126	74.73 283	83.73 339	51.79 295	88.73 320	70.78 214	72.15 377	88.55 300

WR-MVS_H		78.51 222	78.49 197	78.56 302	88.02 199	56.38 361	88.43 143	92.67 68	77.14 64	73.89 294	87.55 241	66.25 125	89.24 309	58.92 326	73.55 366	90.06 243

RPSCF		73.23 316	71.46 320	78.54 303	82.50 354	59.85 314	82.18 315	82.84 339	58.96 388	71.15 330	89.41 188	45.48 363	84.77 367	58.82 328	71.83 380	91.02 198

testing11		75.14 291	74.01 289	78.53 304	88.16 190	56.38 361	80.74 335	80.42 367	70.67 221	72.69 311	83.72 340	43.61 375	89.86 296	62.29 294	83.76 226	89.36 268

pmmvs-eth3d		70.50 344	67.83 358	78.52 305	77.37 409	66.18 187	81.82 317	81.51 352	58.90 389	63.90 403	80.42 384	42.69 380	86.28 349	58.56 330	65.30 407	83.11 397

PatchmatchNet		73.12 317	71.33 323	78.49 306	83.18 335	60.85 301	79.63 351	78.57 386	64.13 335	71.73 322	79.81 394	51.20 301	85.97 353	57.40 342	76.36 330	88.66 295
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
reproduce_monomvs		75.40 288	74.38 286	78.46 307	83.92 318	57.80 339	83.78 286	86.94 271	73.47 164	72.25 317	84.47 319	38.74 402	89.27 308	75.32 167	70.53 387	88.31 304

IterMVS		74.29 297	72.94 305	78.35 308	81.53 369	63.49 258	81.58 321	82.49 341	68.06 287	69.99 342	83.69 341	51.66 297	85.54 358	65.85 265	71.64 381	86.01 356
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ITE_SJBPF				78.22 309	81.77 364	60.57 305		83.30 325	69.25 262	67.54 365	87.20 251	36.33 414	87.28 340	54.34 363	74.62 356	86.80 341

testing222		74.04 302	72.66 308	78.19 310	87.89 205	55.36 375	81.06 329	79.20 382	71.30 205	74.65 285	83.57 345	39.11 401	88.67 322	51.43 380	85.75 195	90.53 218

ppachtmachnet_test		70.04 350	67.34 368	78.14 311	79.80 393	61.13 295	79.19 358	80.59 362	59.16 386	65.27 392	79.29 397	46.75 346	87.29 339	49.33 393	66.72 400	86.00 358

mamba_test_0407_2		77.67 247	77.52 228	78.12 312	88.81 163	67.96 145	65.03 440	88.66 230	70.96 216	79.48 165	89.80 170	58.69 222	74.23 432	70.35 221	85.93 191	92.18 159

tfpnnormal		74.39 296	73.16 302	78.08 313	86.10 266	58.05 331	84.65 267	87.53 257	70.32 235	71.22 329	85.63 294	54.97 253	89.86 296	43.03 421	75.02 352	86.32 348

tt0320-xc		70.11 349	67.45 366	78.07 314	85.33 284	59.51 320	83.28 300	78.96 384	58.77 390	67.10 373	80.28 387	36.73 411	87.42 338	56.83 350	59.77 422	87.29 327

Vis-MVSNet (Re-imp)		78.36 225	78.45 198	78.07 314	88.64 173	51.78 405	86.70 208	79.63 377	74.14 145	75.11 274	90.83 147	61.29 194	89.75 299	58.10 336	91.60 92	92.69 134

tt0320		70.49 345	68.03 353	77.89 316	84.78 298	59.12 322	83.55 294	80.44 366	58.13 396	67.43 369	80.41 385	39.26 399	87.54 337	55.12 358	63.18 413	86.99 337

TransMVSNet (Re)		75.39 289	74.56 282	77.86 317	85.50 280	57.10 349	86.78 205	86.09 288	72.17 188	71.53 325	87.34 245	63.01 163	89.31 307	56.84 349	61.83 415	87.17 330

PEN-MVS		77.73 242	77.69 224	77.84 318	87.07 244	53.91 389	87.91 166	91.18 131	77.56 51	73.14 304	88.82 203	61.23 195	89.17 311	59.95 315	72.37 374	90.43 222

CP-MVSNet		78.22 227	78.34 202	77.84 318	87.83 209	54.54 384	87.94 164	91.17 132	77.65 46	73.48 300	88.49 213	62.24 174	88.43 325	62.19 295	74.07 359	90.55 217

PS-CasMVS		78.01 236	78.09 208	77.77 320	87.71 216	54.39 386	88.02 160	91.22 129	77.50 54	73.26 302	88.64 208	60.73 202	88.41 326	61.88 299	73.88 363	90.53 218

baseline1		76.98 259	76.75 247	77.66 321	88.13 193	55.66 372	85.12 254	81.89 347	73.04 175	76.79 225	88.90 200	62.43 170	87.78 334	63.30 284	71.18 384	89.55 263

OpenMVS_ROB	64.09 19	70.56 343	68.19 349	77.65 322	80.26 384	59.41 321	85.01 257	82.96 336	58.76 391	65.43 391	82.33 365	37.63 409	91.23 270	45.34 417	76.03 332	82.32 405

Patchmatch-RL test		70.24 347	67.78 360	77.61 323	77.43 408	59.57 319	71.16 415	70.33 422	62.94 351	68.65 356	72.77 428	50.62 307	85.49 359	69.58 231	66.58 402	87.77 315

Baseline_NR-MVSNet		78.15 231	78.33 203	77.61 323	85.79 270	56.21 365	86.78 205	85.76 292	73.60 159	77.93 199	87.57 239	65.02 139	88.99 314	67.14 255	75.33 347	87.63 317

mmtdpeth		74.16 300	73.01 304	77.60 325	83.72 323	61.13 295	85.10 255	85.10 299	72.06 190	77.21 219	80.33 386	43.84 373	85.75 354	77.14 144	52.61 434	85.91 359

DTE-MVSNet		76.99 258	76.80 243	77.54 326	86.24 259	53.06 398	87.52 176	90.66 145	77.08 68	72.50 312	88.67 207	60.48 210	89.52 303	57.33 343	70.74 386	90.05 244

LCM-MVSNet-Re		77.05 257	76.94 240	77.36 327	87.20 234	51.60 406	80.06 346	80.46 365	75.20 114	67.69 364	86.72 262	62.48 168	88.98 315	63.44 282	89.25 134	91.51 180

tpm cat1		70.57 342	68.31 348	77.35 328	82.41 357	57.95 335	78.08 375	80.22 371	52.04 420	68.54 358	77.66 411	52.00 289	87.84 333	51.77 375	72.07 379	86.25 349

MS-PatchMatch		73.83 305	72.67 307	77.30 329	83.87 319	66.02 189	81.82 317	84.66 304	61.37 369	68.61 357	82.82 359	47.29 338	88.21 327	59.27 321	84.32 218	77.68 424

EPNet_dtu		75.46 285	74.86 277	77.23 330	82.57 353	54.60 383	86.89 200	83.09 331	71.64 194	66.25 386	85.86 288	55.99 247	88.04 330	54.92 360	86.55 178	89.05 277
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_lstm_enhance		74.11 301	73.11 303	77.13 331	80.11 387	59.62 317	72.23 411	86.92 273	66.76 299	70.40 334	82.92 356	56.93 241	82.92 380	69.06 236	72.63 373	88.87 286

TDRefinement		67.49 369	64.34 380	76.92 332	73.47 428	61.07 298	84.86 261	82.98 335	59.77 380	58.30 423	85.13 308	26.06 432	87.89 332	47.92 404	60.59 420	81.81 410

JIA-IIPM		66.32 379	62.82 391	76.82 333	77.09 410	61.72 291	65.34 438	75.38 406	58.04 398	64.51 397	62.32 438	42.05 386	86.51 346	51.45 379	69.22 393	82.21 406

PatchMatch-RL		72.38 324	70.90 328	76.80 334	88.60 174	67.38 165	79.53 352	76.17 405	62.75 355	69.36 350	82.00 372	45.51 361	84.89 366	53.62 367	80.58 273	78.12 423

tpmvs		71.09 336	69.29 341	76.49 335	82.04 360	56.04 366	78.92 363	81.37 355	64.05 339	67.18 372	78.28 406	49.74 320	89.77 298	49.67 391	72.37 374	83.67 391

CMPMVS	51.72 21	70.19 348	68.16 350	76.28 336	73.15 431	57.55 343	79.47 353	83.92 315	48.02 429	56.48 429	84.81 315	43.13 377	86.42 348	62.67 290	81.81 259	84.89 376
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC		70.33 346	68.37 347	76.21 337	80.60 381	56.23 364	79.19 358	86.49 279	60.89 370	61.29 412	85.47 299	31.78 424	89.47 305	53.37 369	76.21 331	82.94 401

gg-mvs-nofinetune		69.95 351	67.96 354	75.94 338	83.07 338	54.51 385	77.23 384	70.29 423	63.11 347	70.32 335	62.33 437	43.62 374	88.69 321	53.88 366	87.76 158	84.62 380

ETVMVS		72.25 327	71.05 326	75.84 339	87.77 214	51.91 402	79.39 354	74.98 408	69.26 261	73.71 296	82.95 355	40.82 393	86.14 350	46.17 411	84.43 216	89.47 264

MDA-MVSNet-bldmvs		66.68 375	63.66 385	75.75 340	79.28 400	60.56 306	73.92 407	78.35 388	64.43 331	50.13 438	79.87 393	44.02 372	83.67 373	46.10 412	56.86 424	83.03 399

PVSNet	64.34 18	72.08 330	70.87 329	75.69 341	86.21 260	56.44 359	74.37 405	80.73 360	62.06 363	70.17 338	82.23 368	42.86 379	83.31 378	54.77 361	84.45 215	87.32 326

pmmvs5		71.55 332	70.20 337	75.61 342	77.83 406	56.39 360	81.74 319	80.89 357	57.76 399	67.46 367	84.49 318	49.26 327	85.32 362	57.08 345	75.29 348	85.11 373

our_test_3		69.14 357	67.00 370	75.57 343	79.80 393	58.80 323	77.96 377	77.81 390	59.55 382	62.90 408	78.25 407	47.43 337	83.97 371	51.71 376	67.58 399	83.93 388

WTY-MVS		75.65 282	75.68 262	75.57 343	86.40 257	56.82 352	77.92 379	82.40 342	65.10 323	76.18 243	87.72 234	63.13 162	80.90 394	60.31 313	81.96 256	89.00 281

UBG		73.08 318	72.27 313	75.51 345	88.02 199	51.29 410	78.35 373	77.38 396	65.52 319	73.87 295	82.36 364	45.55 360	86.48 347	55.02 359	84.39 217	88.75 292

Patchmtry		70.74 340	69.16 343	75.49 346	80.72 379	54.07 388	74.94 402	80.30 369	58.34 393	70.01 340	81.19 374	52.50 278	86.54 345	53.37 369	71.09 385	85.87 361

mvs5depth		69.45 355	67.45 366	75.46 347	73.93 422	55.83 369	79.19 358	83.23 327	66.89 296	71.63 324	83.32 348	33.69 420	85.09 363	59.81 317	55.34 430	85.46 365

GG-mvs-BLEND				75.38 348	81.59 367	55.80 370	79.32 355	69.63 425		67.19 371	73.67 426	43.24 376	88.90 319	50.41 383	84.50 211	81.45 411

WBMVS		73.43 310	72.81 306	75.28 349	87.91 204	50.99 412	78.59 369	81.31 356	65.51 321	74.47 288	84.83 314	46.39 347	86.68 344	58.41 332	77.86 303	88.17 308

ambc				75.24 350	73.16 430	50.51 415	63.05 444	87.47 259		64.28 398	77.81 410	17.80 446	89.73 300	57.88 338	60.64 419	85.49 364

CL-MVSNet_self_test		72.37 325	71.46 320	75.09 351	79.49 398	53.53 391	80.76 334	85.01 302	69.12 267	70.51 332	82.05 370	57.92 229	84.13 370	52.27 374	66.00 405	87.60 318

XXY-MVS		75.41 287	75.56 265	74.96 352	83.59 325	57.82 338	80.59 338	83.87 317	66.54 307	74.93 280	88.31 218	63.24 156	80.09 397	62.16 296	76.85 317	86.97 338

testing3-2		75.12 292	75.19 274	74.91 353	90.40 105	45.09 435	80.29 344	78.42 387	78.37 40	76.54 234	87.75 233	44.36 369	87.28 340	57.04 346	83.49 235	92.37 148

MIMVSNet		70.69 341	69.30 340	74.88 354	84.52 305	56.35 363	75.87 393	79.42 378	64.59 329	67.76 362	82.41 363	41.10 390	81.54 389	46.64 409	81.34 261	86.75 343

ADS-MVSNet2		66.20 382	63.33 386	74.82 355	79.92 389	58.75 324	67.55 430	75.19 407	53.37 417	65.25 393	75.86 419	42.32 382	80.53 396	41.57 425	68.91 394	85.18 370

TinyColmap		67.30 372	64.81 378	74.76 356	81.92 363	56.68 356	80.29 344	81.49 353	60.33 374	56.27 430	83.22 349	24.77 436	87.66 336	45.52 415	69.47 391	79.95 419

test_vis1_n_1920		75.52 284	75.78 260	74.75 357	79.84 391	57.44 345	83.26 301	85.52 294	62.83 353	79.34 169	86.17 283	45.10 364	79.71 398	78.75 124	81.21 264	87.10 336

test-LLR		72.94 321	72.43 310	74.48 358	81.35 373	58.04 332	78.38 370	77.46 393	66.66 301	69.95 343	79.00 400	48.06 335	79.24 399	66.13 260	84.83 206	86.15 352

test-mter		71.41 333	70.39 335	74.48 358	81.35 373	58.04 332	78.38 370	77.46 393	60.32 375	69.95 343	79.00 400	36.08 415	79.24 399	66.13 260	84.83 206	86.15 352

tpm		72.37 325	71.71 317	74.35 360	82.19 359	52.00 400	79.22 357	77.29 397	64.56 330	72.95 307	83.68 342	51.35 298	83.26 379	58.33 334	75.80 334	87.81 314

SD_0403		74.65 295	74.77 279	74.29 361	86.20 261	47.42 424	83.71 288	85.12 298	69.30 259	68.50 359	87.95 231	59.40 218	86.05 351	49.38 392	83.35 238	89.40 266

CVMVSNet		72.99 320	72.58 309	74.25 362	84.28 308	50.85 413	86.41 217	83.45 324	44.56 433	73.23 303	87.54 242	49.38 324	85.70 355	65.90 264	78.44 297	86.19 351

FMVSNet5		69.50 354	67.96 354	74.15 363	82.97 344	55.35 376	80.01 348	82.12 345	62.56 357	63.02 405	81.53 373	36.92 410	81.92 387	48.42 397	74.06 360	85.17 372

UWE-MVS		72.13 329	71.49 319	74.03 364	86.66 253	47.70 422	81.40 326	76.89 401	63.60 344	75.59 252	84.22 329	39.94 396	85.62 357	48.98 395	86.13 186	88.77 291

MIMVSNet1		68.58 362	66.78 372	73.98 365	80.07 388	51.82 404	80.77 333	84.37 307	64.40 332	59.75 419	82.16 369	36.47 413	83.63 374	42.73 422	70.33 388	86.48 347

myMVS_eth3d28		73.62 307	73.53 297	73.90 366	88.20 188	47.41 425	78.06 376	79.37 379	74.29 141	73.98 293	84.29 325	44.67 365	83.54 375	51.47 378	87.39 163	90.74 209

test_cas_vis1_n_1920		73.76 306	73.74 295	73.81 367	75.90 413	59.77 315	80.51 339	82.40 342	58.30 394	81.62 133	85.69 291	44.35 370	76.41 416	76.29 153	78.61 293	85.23 369

Anonymous20240521		68.80 360	67.22 369	73.55 368	74.33 420	54.11 387	83.18 302	85.61 293	58.15 395	61.68 411	80.94 379	30.71 427	81.27 392	57.00 347	73.34 370	85.28 368

sss		73.60 308	73.64 296	73.51 369	82.80 347	55.01 380	76.12 389	81.69 350	62.47 358	74.68 284	85.85 289	57.32 236	78.11 405	60.86 309	80.93 266	87.39 323

SSC-MVS3.2		73.35 314	73.39 298	73.23 370	85.30 285	49.01 420	74.58 404	81.57 351	75.21 113	73.68 297	85.58 296	52.53 276	82.05 386	54.33 364	77.69 307	88.63 297

KD-MVS_2432*1600		66.22 380	63.89 383	73.21 371	75.47 418	53.42 393	70.76 418	84.35 308	64.10 337	66.52 382	78.52 404	34.55 418	84.98 364	50.40 384	50.33 437	81.23 412

miper_refine_blended		66.22 380	63.89 383	73.21 371	75.47 418	53.42 393	70.76 418	84.35 308	64.10 337	66.52 382	78.52 404	34.55 418	84.98 364	50.40 384	50.33 437	81.23 412

PM-MVS		66.41 378	64.14 381	73.20 373	73.92 423	56.45 358	78.97 362	64.96 439	63.88 343	64.72 396	80.24 388	19.84 444	83.44 377	66.24 259	64.52 409	79.71 420

tpmrst		72.39 323	72.13 314	73.18 374	80.54 382	49.91 417	79.91 350	79.08 383	63.11 347	71.69 323	79.95 391	55.32 251	82.77 382	65.66 267	73.89 362	86.87 339

WB-MVSnew		71.96 331	71.65 318	72.89 375	84.67 304	51.88 403	82.29 314	77.57 392	62.31 359	73.67 298	83.00 354	53.49 272	81.10 393	45.75 414	82.13 254	85.70 362

dmvs_re		71.14 335	70.58 330	72.80 376	81.96 361	59.68 316	75.60 395	79.34 380	68.55 279	69.27 352	80.72 382	49.42 323	76.54 413	52.56 373	77.79 304	82.19 407

test_fmvs1_n		70.86 339	70.24 336	72.73 377	72.51 435	55.28 377	81.27 327	79.71 376	51.49 424	78.73 176	84.87 313	27.54 431	77.02 410	76.06 156	79.97 282	85.88 360

TESTMET0.1,1		69.89 352	69.00 344	72.55 378	79.27 401	56.85 351	78.38 370	74.71 412	57.64 400	68.09 361	77.19 413	37.75 408	76.70 412	63.92 279	84.09 221	84.10 386

mamv4		76.81 262	78.23 207	72.54 379	86.12 264	65.75 200	78.76 365	82.07 346	64.12 336	72.97 306	91.02 143	67.97 105	68.08 444	83.04 82	78.02 302	83.80 390

KD-MVS_self_test		68.81 359	67.59 364	72.46 380	74.29 421	45.45 430	77.93 378	87.00 269	63.12 346	63.99 402	78.99 402	42.32 382	84.77 367	56.55 353	64.09 410	87.16 332

test_fmvs1		70.93 338	70.52 331	72.16 381	73.71 424	55.05 379	80.82 330	78.77 385	51.21 425	78.58 181	84.41 321	31.20 426	76.94 411	75.88 159	80.12 281	84.47 381

CHOSEN 280x420		66.51 377	64.71 379	71.90 382	81.45 370	63.52 257	57.98 446	68.95 429	53.57 416	62.59 409	76.70 414	46.22 352	75.29 428	55.25 357	79.68 283	76.88 426

test_vis1_n		69.85 353	69.21 342	71.77 383	72.66 434	55.27 378	81.48 323	76.21 404	52.03 421	75.30 268	83.20 351	28.97 429	76.22 418	74.60 173	78.41 299	83.81 389

EPMVS		69.02 358	68.16 350	71.59 384	79.61 396	49.80 419	77.40 382	66.93 433	62.82 354	70.01 340	79.05 398	45.79 357	77.86 407	56.58 352	75.26 349	87.13 333

YYNet1		65.03 384	62.91 389	71.38 385	75.85 414	56.60 357	69.12 426	74.66 413	57.28 404	54.12 432	77.87 409	45.85 356	74.48 430	49.95 389	61.52 417	83.05 398

MDA-MVSNet_test_wron		65.03 384	62.92 388	71.37 386	75.93 412	56.73 353	69.09 427	74.73 411	57.28 404	54.03 433	77.89 408	45.88 355	74.39 431	49.89 390	61.55 416	82.99 400

UnsupCasMVSNet_eth		67.33 371	65.99 375	71.37 386	73.48 427	51.47 408	75.16 398	85.19 297	65.20 322	60.78 414	80.93 381	42.35 381	77.20 409	57.12 344	53.69 432	85.44 366

PMMVS		69.34 356	68.67 345	71.35 388	75.67 415	62.03 285	75.17 397	73.46 415	50.00 426	68.68 355	79.05 398	52.07 288	78.13 404	61.16 307	82.77 246	73.90 430

EU-MVSNet		68.53 364	67.61 363	71.31 389	78.51 405	47.01 427	84.47 271	84.27 311	42.27 436	66.44 385	84.79 316	40.44 394	83.76 372	58.76 329	68.54 397	83.17 395

testing3		68.56 363	67.67 362	71.22 390	87.33 230	42.87 440	83.06 308	71.54 420	70.36 232	69.08 353	84.38 322	30.33 428	85.69 356	37.50 433	75.45 343	85.09 374

Anonymous20231206		68.60 361	67.80 359	71.02 391	80.23 386	50.75 414	78.30 374	80.47 364	56.79 406	66.11 388	82.63 362	46.35 350	78.95 401	43.62 420	75.70 335	83.36 394

test_fmvs2		68.35 366	67.48 365	70.98 392	69.50 438	51.95 401	80.05 347	76.38 403	49.33 427	74.65 285	84.38 322	23.30 440	75.40 427	74.51 174	75.17 351	85.60 363

dp		66.80 374	65.43 376	70.90 393	79.74 395	48.82 421	75.12 400	74.77 410	59.61 381	64.08 401	77.23 412	42.89 378	80.72 395	48.86 396	66.58 402	83.16 396

PatchT		68.46 365	67.85 356	70.29 394	80.70 380	43.93 438	72.47 410	74.88 409	60.15 377	70.55 331	76.57 415	49.94 317	81.59 388	50.58 382	74.83 354	85.34 367

UnsupCasMVSNet_bld		63.70 389	61.53 395	70.21 395	73.69 425	51.39 409	72.82 409	81.89 347	55.63 411	57.81 425	71.80 430	38.67 403	78.61 402	49.26 394	52.21 435	80.63 416

Patchmatch-test		64.82 386	63.24 387	69.57 396	79.42 399	49.82 418	63.49 443	69.05 428	51.98 422	59.95 418	80.13 389	50.91 303	70.98 437	40.66 427	73.57 365	87.90 312

LF4IMVS		64.02 388	62.19 392	69.50 397	70.90 436	53.29 396	76.13 388	77.18 398	52.65 419	58.59 421	80.98 378	23.55 439	76.52 414	53.06 371	66.66 401	78.68 422

myMVS_eth3d		67.02 373	66.29 374	69.21 398	84.68 301	42.58 441	78.62 367	73.08 417	66.65 304	66.74 378	79.46 395	31.53 425	82.30 384	39.43 430	76.38 328	82.75 402

test20.03		67.45 370	66.95 371	68.94 399	75.48 417	44.84 436	77.50 381	77.67 391	66.66 301	63.01 406	83.80 336	47.02 341	78.40 403	42.53 424	68.86 396	83.58 392

test0.0.03 1		68.00 368	67.69 361	68.90 400	77.55 407	47.43 423	75.70 394	72.95 419	66.66 301	66.56 380	82.29 367	48.06 335	75.87 422	44.97 418	74.51 357	83.41 393

PVSNet_0	57.27 20	61.67 394	59.27 397	68.85 401	79.61 396	57.44 345	68.01 428	73.44 416	55.93 410	58.54 422	70.41 433	44.58 367	77.55 408	47.01 406	35.91 445	71.55 433

ADS-MVSNet		64.36 387	62.88 390	68.78 402	79.92 389	47.17 426	67.55 430	71.18 421	53.37 417	65.25 393	75.86 419	42.32 382	73.99 433	41.57 425	68.91 394	85.18 370

Syy-MVS		68.05 367	67.85 356	68.67 403	84.68 301	40.97 446	78.62 367	73.08 417	66.65 304	66.74 378	79.46 395	52.11 286	82.30 384	32.89 438	76.38 328	82.75 402

pmmvs3		57.79 398	54.26 403	68.37 404	64.02 446	56.72 354	75.12 400	65.17 437	40.20 438	52.93 434	69.86 434	20.36 443	75.48 425	45.45 416	55.25 431	72.90 432

ttmdpeth		59.91 396	57.10 400	68.34 405	67.13 442	46.65 429	74.64 403	67.41 432	48.30 428	62.52 410	85.04 312	20.40 442	75.93 421	42.55 423	45.90 443	82.44 404

MVStest1		56.63 400	52.76 406	68.25 406	61.67 448	53.25 397	71.67 413	68.90 430	38.59 441	50.59 437	83.05 353	25.08 434	70.66 438	36.76 434	38.56 444	80.83 415

test_fmvs3		63.36 390	61.82 393	67.98 407	62.51 447	46.96 428	77.37 383	74.03 414	45.24 432	67.50 366	78.79 403	12.16 452	72.98 436	72.77 194	66.02 404	83.99 387

LCM-MVSNet		54.25 402	49.68 412	67.97 408	53.73 456	45.28 433	66.85 433	80.78 359	35.96 445	39.45 446	62.23 439	8.70 456	78.06 406	48.24 401	51.20 436	80.57 417

EGC-MVSNET		52.07 409	47.05 413	67.14 409	83.51 327	60.71 303	80.50 340	67.75 431	0.07 459	0.43 460	75.85 421	24.26 437	81.54 389	28.82 442	62.25 414	59.16 442

testgi		66.67 376	66.53 373	67.08 410	75.62 416	41.69 445	75.93 390	76.50 402	66.11 310	65.20 395	86.59 270	35.72 416	74.71 429	43.71 419	73.38 369	84.84 377

UWE-MVS-28		65.32 383	64.93 377	66.49 411	78.70 403	38.55 448	77.86 380	64.39 440	62.00 364	64.13 400	83.60 343	41.44 388	76.00 420	31.39 440	80.89 267	84.92 375

test_vis1_rt		60.28 395	58.42 398	65.84 412	67.25 441	55.60 373	70.44 420	60.94 445	44.33 434	59.00 420	66.64 435	24.91 435	68.67 442	62.80 286	69.48 390	73.25 431

mvsany_test1		62.30 392	61.26 396	65.41 413	69.52 437	54.86 381	66.86 432	49.78 453	46.65 430	68.50 359	83.21 350	49.15 328	66.28 445	56.93 348	60.77 418	75.11 429

ANet_high		50.57 411	46.10 415	63.99 414	48.67 459	39.13 447	70.99 417	80.85 358	61.39 368	31.18 448	57.70 444	17.02 447	73.65 435	31.22 441	15.89 456	79.18 421

MVS-HIRNet		59.14 397	57.67 399	63.57 415	81.65 365	43.50 439	71.73 412	65.06 438	39.59 440	51.43 435	57.73 443	38.34 405	82.58 383	39.53 428	73.95 361	64.62 439

APD_test1		53.31 406	49.93 411	63.42 416	65.68 443	50.13 416	71.59 414	66.90 434	34.43 446	40.58 445	71.56 431	8.65 457	76.27 417	34.64 437	55.36 429	63.86 440

new-patchmatchnet		61.73 393	61.73 394	61.70 417	72.74 433	24.50 460	69.16 425	78.03 389	61.40 367	56.72 428	75.53 422	38.42 404	76.48 415	45.95 413	57.67 423	84.13 385

mvsany_test3		53.99 403	51.45 408	61.61 418	55.51 452	44.74 437	63.52 442	45.41 457	43.69 435	58.11 424	76.45 416	17.99 445	63.76 448	54.77 361	47.59 439	76.34 427

DSMNet-mixed		57.77 399	56.90 401	60.38 419	67.70 440	35.61 450	69.18 424	53.97 451	32.30 449	57.49 426	79.88 392	40.39 395	68.57 443	38.78 431	72.37 374	76.97 425

FPMVS		53.68 405	51.64 407	59.81 420	65.08 444	51.03 411	69.48 423	69.58 426	41.46 437	40.67 444	72.32 429	16.46 448	70.00 441	24.24 448	65.42 406	58.40 444

dmvs_testset		62.63 391	64.11 382	58.19 421	78.55 404	24.76 459	75.28 396	65.94 436	67.91 288	60.34 415	76.01 418	53.56 270	73.94 434	31.79 439	67.65 398	75.88 428

testf1		45.72 413	41.96 417	57.00 422	56.90 450	45.32 431	66.14 435	59.26 447	26.19 450	30.89 449	60.96 441	4.14 460	70.64 439	26.39 446	46.73 441	55.04 445

APD_test2		45.72 413	41.96 417	57.00 422	56.90 450	45.32 431	66.14 435	59.26 447	26.19 450	30.89 449	60.96 441	4.14 460	70.64 439	26.39 446	46.73 441	55.04 445

test_vis3_rt		49.26 412	47.02 414	56.00 424	54.30 453	45.27 434	66.76 434	48.08 454	36.83 443	44.38 442	53.20 447	7.17 459	64.07 447	56.77 351	55.66 427	58.65 443

test_f		52.09 408	50.82 409	55.90 425	53.82 455	42.31 444	59.42 445	58.31 449	36.45 444	56.12 431	70.96 432	12.18 451	57.79 451	53.51 368	56.57 426	67.60 436

PMVS	37.38 22	44.16 417	40.28 421	55.82 426	40.82 461	42.54 443	65.12 439	63.99 441	34.43 446	24.48 452	57.12 445	3.92 462	76.17 419	17.10 453	55.52 428	48.75 447
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
WB-MVS		54.94 401	54.72 402	55.60 427	73.50 426	20.90 461	74.27 406	61.19 444	59.16 386	50.61 436	74.15 424	47.19 340	75.78 423	17.31 452	35.07 446	70.12 434

Gipuma		45.18 416	41.86 419	55.16 428	77.03 411	51.52 407	32.50 452	80.52 363	32.46 448	27.12 451	35.02 452	9.52 455	75.50 424	22.31 449	60.21 421	38.45 451
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SSC-MVS		53.88 404	53.59 404	54.75 429	72.87 432	19.59 462	73.84 408	60.53 446	57.58 402	49.18 440	73.45 427	46.34 351	75.47 426	16.20 455	32.28 448	69.20 435

new_pmnet		50.91 410	50.29 410	52.78 430	68.58 439	34.94 452	63.71 441	56.63 450	39.73 439	44.95 441	65.47 436	21.93 441	58.48 450	34.98 436	56.62 425	64.92 438

N_pmnet		52.79 407	53.26 405	51.40 431	78.99 402	7.68 465	69.52 422	3.89 464	51.63 423	57.01 427	74.98 423	40.83 392	65.96 446	37.78 432	64.67 408	80.56 418

PMMVS2		40.82 418	38.86 422	46.69 432	53.84 454	16.45 463	48.61 449	49.92 452	37.49 442	31.67 447	60.97 440	8.14 458	56.42 452	28.42 443	30.72 449	67.19 437

dongtai		45.42 415	45.38 416	45.55 433	73.36 429	26.85 457	67.72 429	34.19 459	54.15 415	49.65 439	56.41 446	25.43 433	62.94 449	19.45 450	28.09 450	46.86 449

MVE	26.22 23	30.37 423	25.89 427	43.81 434	44.55 460	35.46 451	28.87 453	39.07 458	18.20 454	18.58 456	40.18 451	2.68 463	47.37 456	17.07 454	23.78 453	48.60 448
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		31.52 421	29.28 425	38.23 435	27.03 463	6.50 466	20.94 454	62.21 443	4.05 457	22.35 455	52.50 448	13.33 449	47.58 455	27.04 445	34.04 447	60.62 441

kuosan		39.70 419	40.40 420	37.58 436	64.52 445	26.98 455	65.62 437	33.02 460	46.12 431	42.79 443	48.99 449	24.10 438	46.56 457	12.16 458	26.30 451	39.20 450

E-PMN		31.77 420	30.64 423	35.15 437	52.87 457	27.67 454	57.09 447	47.86 455	24.64 452	16.40 457	33.05 453	11.23 453	54.90 453	14.46 456	18.15 454	22.87 453

EMVS		30.81 422	29.65 424	34.27 438	50.96 458	25.95 458	56.58 448	46.80 456	24.01 453	15.53 458	30.68 454	12.47 450	54.43 454	12.81 457	17.05 455	22.43 454

DeepMVS_CX				27.40 439	40.17 462	26.90 456		24.59 463	17.44 455	23.95 453	48.61 450	9.77 454	26.48 458	18.06 451	24.47 452	28.83 452

wuyk23d		16.82 426	15.94 429	19.46 440	58.74 449	31.45 453	39.22 450	3.74 465	6.84 456	6.04 459	2.70 459	1.27 464	24.29 459	10.54 459	14.40 458	2.63 456

tmp_tt		18.61 425	21.40 428	10.23 441	4.82 464	10.11 464	34.70 451	30.74 462	1.48 458	23.91 454	26.07 455	28.42 430	13.41 460	27.12 444	15.35 457	7.17 455

test123		6.12 428	8.11 431	0.14 442	0.06 466	0.09 467	71.05 416	0.03 467	0.04 461	0.25 462	1.30 461	0.05 465	0.03 462	0.21 461	0.01 460	0.29 457

testmvs		6.04 429	8.02 432	0.10 443	0.08 465	0.03 468	69.74 421	0.04 466	0.05 460	0.31 461	1.68 460	0.02 466	0.04 461	0.24 460	0.02 459	0.25 458

mmdepth		0.00 431	0.00 434	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	0.00 462	0.00 467	0.00 463	0.00 462	0.00 461	0.00 459

monomultidepth		0.00 431	0.00 434	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	0.00 462	0.00 467	0.00 463	0.00 462	0.00 461	0.00 459

test_blank		0.00 431	0.00 434	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	0.00 462	0.00 467	0.00 463	0.00 462	0.00 461	0.00 459

uanet_test		0.00 431	0.00 434	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	0.00 462	0.00 467	0.00 463	0.00 462	0.00 461	0.00 459

DCPMVS		0.00 431	0.00 434	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	0.00 462	0.00 467	0.00 463	0.00 462	0.00 461	0.00 459

cdsmvs_eth3d_5k		19.96 424	26.61 426	0.00 444	0.00 467	0.00 469	0.00 455	89.26 201	0.00 462	0.00 463	88.61 209	61.62 185	0.00 463	0.00 462	0.00 461	0.00 459

pcd_1.5k_mvsjas		5.26 430	7.02 433	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	0.00 462	63.15 159	0.00 463	0.00 462	0.00 461	0.00 459

sosnet-low-res		0.00 431	0.00 434	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	0.00 462	0.00 467	0.00 463	0.00 462	0.00 461	0.00 459

sosnet		0.00 431	0.00 434	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	0.00 462	0.00 467	0.00 463	0.00 462	0.00 461	0.00 459

uncertanet		0.00 431	0.00 434	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	0.00 462	0.00 467	0.00 463	0.00 462	0.00 461	0.00 459

Regformer		0.00 431	0.00 434	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	0.00 462	0.00 467	0.00 463	0.00 462	0.00 461	0.00 459

ab-mvs-re		7.23 427	9.64 430	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	86.72 262	0.00 467	0.00 463	0.00 462	0.00 461	0.00 459

uanet		0.00 431	0.00 434	0.00 444	0.00 467	0.00 469	0.00 455	0.00 468	0.00 462	0.00 463	0.00 462	0.00 467	0.00 463	0.00 462	0.00 461	0.00 459

WAC-MVS						42.58 441								39.46 429

FOURS1					95.00 10	72.39 41	95.06 1	93.84 16	74.49 134	91.30 15

PC_three_1452									68.21 285	92.02 12	94.00 56	82.09 5	95.98 57	84.58 64	96.68 2	94.95 12

test_one_0601					95.07 7	71.46 59		94.14 6	78.27 41	92.05 11	95.74 6	80.83 11

eth-test2					0.00 467

eth-test					0.00 467

ZD-MVS					94.38 25	72.22 46		92.67 68	70.98 215	87.75 44	94.07 51	74.01 33	96.70 27	84.66 63	94.84 44

RE-MVS-def			85.48 69		93.06 60	70.63 78	91.88 39	92.27 85	73.53 162	85.69 66	94.45 32	63.87 149		82.75 86	91.87 88	92.50 142

IU-MVS					95.30 2	71.25 61		92.95 56	66.81 297	92.39 6				88.94 25	96.63 4	94.85 21

test_241102_TWO								94.06 11	77.24 60	92.78 4	95.72 8	81.26 8	97.44 7	89.07 22	96.58 6	94.26 52

test_241102_ONE					95.30 2	70.98 68		94.06 11	77.17 63	93.10 1	95.39 16	82.99 1	97.27 12

9.14			88.26 16		92.84 65		91.52 51	94.75 1	73.93 150	88.57 29	94.67 25	75.57 22	95.79 59	86.77 45	95.76 23

save fliter					93.80 40	72.35 44	90.47 69	91.17 132	74.31 139

test_0728_THIRD									78.38 38	92.12 9	95.78 4	81.46 7	97.40 9	89.42 17	96.57 7	94.67 29

test0726					95.27 5	71.25 61	93.60 7	94.11 7	77.33 57	92.81 3	95.79 3	80.98 9

GSMVS																88.96 283

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs1												51.32 299				88.96 283

sam_mvs												50.01 315

MTGPA								92.02 98

test_post1							78.90 364				5.43 458	48.81 334	85.44 361	59.25 322

test_post											5.46 457	50.36 311	84.24 369

patchmatchnet-post											74.00 425	51.12 302	88.60 323

MTMP							92.18 35	32.83 461

gm-plane-assit					81.40 371	53.83 390			62.72 356		80.94 379		92.39 220	63.40 283

test9_res														84.90 57	95.70 26	92.87 127

TEST9					93.26 52	72.96 25	88.75 131	91.89 106	68.44 282	85.00 73	93.10 81	74.36 29	95.41 76

test_8					93.13 56	72.57 35	88.68 136	91.84 110	68.69 277	84.87 77	93.10 81	74.43 27	95.16 86

agg_prior2														82.91 84	95.45 29	92.70 132

agg_prior					92.85 64	71.94 52		91.78 113		84.41 88			94.93 97

test_prior4						72.60 34	89.01 118

test_prior2							88.85 125		75.41 107	84.91 75	93.54 69	74.28 30		83.31 78	95.86 20

旧先验2							86.56 213		58.10 397	87.04 55			88.98 315	74.07 179

新几何2							86.29 223

旧先验1					91.96 76	65.79 198		86.37 282			93.08 85	69.31 88			92.74 76	88.74 294

无先验							87.48 177	88.98 216	60.00 378				94.12 133	67.28 252		88.97 282

原ACMM2							86.86 201

test222					91.50 82	68.26 133	84.16 281	83.20 330	54.63 414	79.74 160	91.63 119	58.97 221			91.42 96	86.77 342

testdata2													91.01 278	62.37 293

segment_acmp												73.08 40

testdata1							84.14 282		75.71 100

plane_prior7					90.08 112	68.51 127

plane_prior6					89.84 121	68.70 121						60.42 211

plane_prior5								92.44 78					95.38 78	78.71 125	86.32 181	91.33 186

plane_prior4											91.00 144

plane_prior3						68.60 124			78.44 36	78.92 174

plane_prior2							91.25 55		79.12 28

plane_prior1					89.90 120

plane_prior						68.71 119	90.38 73		77.62 47						86.16 185

n2								0.00 468

nn								0.00 468

door-mid								69.98 424

test11								92.23 88

door								69.44 427

HQP5-MVS						66.98 176

HQP-NCC					89.33 140		89.17 109		76.41 85	77.23 215

ACMP_Plane					89.33 140		89.17 109		76.41 85	77.23 215

BP-MVS														77.47 139

HQP4-MVS										77.24 214			95.11 90			91.03 196

HQP3-MVS								92.19 92							85.99 189

HQP2-MVS												60.17 214

NP-MVS					89.62 125	68.32 131					90.24 160

MDTV_nov1_ep13_2view						37.79 449	75.16 398		55.10 412	66.53 381		49.34 325		53.98 365		87.94 311

MDTV_nov1_ep13			69.97 338		83.18 335	53.48 392	77.10 386	80.18 373	60.45 373	69.33 351	80.44 383	48.89 333	86.90 342	51.60 377	78.51 296

ACMMP++_ref															81.95 257

ACMMP++															81.25 262

Test By Simon												64.33 145

High-resolution multi-view benchmark