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.

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	93.05 121

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 43

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 43

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

MTAPA		87.23 33	87.00 36	87.90 22	94.18 35	74.25 5	86.58 213	92.02 98	79.45 22	85.88 63	94.80 23	68.07 105	96.21 46	86.69 46	95.34 32	93.23 107

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 91
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
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	67.93 107	95.95 58	84.20 71	94.39 57	93.23 107

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 49

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 25	93.63 22	74.77 129	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
MM		89.16 6	89.23 7	88.97 4	90.79 98	73.65 10	92.66 24	91.17 133	86.57 1	87.39 51	94.97 21	71.70 57	97.68 1	92.19 1	95.63 28	95.57 1

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 58

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 64

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 62

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	82.81 119	94.25 43	66.44 123	96.24 45	82.88 85	94.28 60	93.38 100

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 84

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	76.66 231	93.37 76	60.40 214	96.75 26	77.20 143	93.73 66	95.29 6

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
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	67.87 109	96.64 31	82.70 90	94.57 52	93.66 84

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 50

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	67.45 112	96.60 33	83.06 80	94.50 53	94.07 60

X-MVStestdata		80.37 179	77.83 217	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 106	12.47 458	67.45 112	96.60 33	83.06 80	94.50 53	94.07 60

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 59

DPM-MVS		84.93 80	84.29 87	86.84 52	90.20 109	73.04 23	87.12 190	93.04 42	69.80 250	82.85 117	91.22 134	73.06 41	96.02 53	76.72 153	94.63 50	91.46 187

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 70

TEST9					93.26 52	72.96 25	88.75 131	91.89 106	68.44 284	85.00 73	93.10 81	74.36 29	95.41 76

train_agg		86.43 46	86.20 50	87.13 45	93.26 52	72.96 25	88.75 131	91.89 106	68.69 279	85.00 73	93.10 81	74.43 27	95.41 76	84.97 56	95.71 25	93.02 123

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.
3Dnovator	76.31 5	83.38 107	82.31 119	86.59 57	87.94 204	72.94 28	90.64 63	92.14 97	77.21 62	75.47 257	92.83 90	58.56 226	94.72 110	73.24 190	92.71 77	92.13 165

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	93.78 152	87.63 39	94.27 61	93.65 88
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
MVS_111021_HR		85.14 76	84.75 81	86.32 61	91.65 81	72.70 30	85.98 230	90.33 159	76.11 94	82.08 126	91.61 122	71.36 63	94.17 133	81.02 102	92.58 78	92.08 166

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 67
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_part2					95.06 8	72.65 32				91.80 13

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	80.73 149	93.82 65	64.33 146	96.29 42	82.67 91	90.69 109	93.23 107
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_prior4						72.60 34	89.01 118

test_8					93.13 56	72.57 35	88.68 136	91.84 110	68.69 279	84.87 77	93.10 81	74.43 27	95.16 86

TSAR-MVS + GP.		85.71 63	85.33 72	86.84 52	91.34 84	72.50 36	89.07 117	87.28 264	76.41 85	85.80 64	90.22 163	74.15 32	95.37 81	81.82 95	91.88 87	92.65 137

CSCG		86.41 48	86.19 52	87.07 46	92.91 63	72.48 37	90.81 61	93.56 25	73.95 149	83.16 112	91.07 140	75.94 18	95.19 85	79.94 116	94.38 58	93.55 95

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	64.64 144	95.53 67	80.70 108	94.65 48	94.56 38

SymmetryMVS		85.38 72	84.81 80	87.07 46	91.47 83	72.47 38	91.65 43	88.06 244	79.31 24	84.39 89	92.18 102	64.64 144	95.53 67	80.70 108	90.91 106	93.21 110

MCST-MVS		87.37 31	87.25 32	87.73 28	94.53 17	72.46 40	89.82 82	93.82 17	73.07 175	84.86 78	92.89 88	76.22 17	96.33 41	84.89 59	95.13 36	94.40 45

FOURS1					95.00 10	72.39 41	95.06 1	93.84 16	74.49 135	91.30 15

APD-MVS		87.44 26	87.52 27	87.19 43	94.24 32	72.39 41	91.86 41	92.83 61	73.01 177	88.58 28	94.52 27	73.36 35	96.49 38	84.26 68	95.01 37	92.70 133
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
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 55
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
save fliter					93.80 40	72.35 44	90.47 69	91.17 133	74.31 140

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	82.82 118	94.23 44	72.13 51	97.09 16	84.83 60	95.37 31	93.65 88
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ZD-MVS					94.38 25	72.22 46		92.67 68	70.98 216	87.75 44	94.07 51	74.01 33	96.70 27	84.66 63	94.84 44

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 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
TSAR-MVS + MP.		88.02 18	88.11 17	87.72 30	93.68 43	72.13 48	91.41 53	92.35 83	74.62 133	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
SR-MVS		86.73 40	86.67 43	86.91 51	94.11 37	72.11 49	92.37 29	92.56 76	74.50 134	86.84 58	94.65 26	67.31 114	95.77 60	84.80 61	92.85 74	92.84 131

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 35
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
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

agg_prior					92.85 64	71.94 52		91.78 113		84.41 88			94.93 97

MVS_0304		87.69 21	87.55 26	88.12 13	89.45 134	71.76 53	91.47 52	89.54 186	82.14 3	86.65 59	94.28 40	68.28 104	97.46 6	90.81 6	95.31 34	95.15 8

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 42
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
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	93.06 119

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	93.06 119

MVS_111021_LR		82.61 121	82.11 121	84.11 138	88.82 162	71.58 57	85.15 254	86.16 288	74.69 130	80.47 154	91.04 141	62.29 173	90.55 289	80.33 112	90.08 120	90.20 234

MAR-MVS		81.84 133	80.70 143	85.27 89	91.32 85	71.53 58	89.82 82	90.92 139	69.77 252	78.50 185	86.21 283	62.36 172	94.52 118	65.36 270	92.05 86	89.77 259
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
test_one_0601					95.07 7	71.46 59		94.14 6	78.27 41	92.05 11	95.74 6	80.83 11

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 54

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

IU-MVS					95.30 2	71.25 61		92.95 56	66.81 299	92.39 6				88.94 25	96.63 4	94.85 21

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	93.33 104
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
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

reproduce_model		87.28 32	87.39 30	86.95 50	93.10 58	71.24 65	91.60 45	93.19 36	74.69 130	88.80 27	95.61 11	70.29 76	96.44 39	86.20 50	93.08 71	93.16 114

CDPH-MVS		85.76 62	85.29 75	87.17 44	93.49 47	71.08 66	88.58 140	92.42 81	68.32 286	84.61 84	93.48 71	72.32 47	96.15 49	79.00 122	95.43 30	94.28 52

CNLPA		78.08 234	76.79 246	81.97 227	90.40 105	71.07 67	87.59 175	84.55 308	66.03 315	72.38 317	89.64 178	57.56 235	86.04 354	59.61 321	83.35 240	88.79 292

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

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

PHI-MVS		86.43 46	86.17 53	87.24 42	90.88 95	70.96 70	92.27 33	94.07 10	72.45 183	85.22 71	91.90 109	69.47 85	96.42 40	83.28 79	95.94 19	94.35 48

OPM-MVS		83.50 103	82.95 108	85.14 92	88.79 168	70.95 71	89.13 114	91.52 122	77.55 52	80.96 145	91.75 114	60.71 204	94.50 119	79.67 119	86.51 180	89.97 251
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
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	81.32 137	91.43 128	70.34 74	97.23 14	84.26 68	93.36 70	94.37 47

DP-MVS Recon		83.11 115	82.09 123	86.15 66	94.44 19	70.92 73	88.79 128	92.20 91	70.53 228	79.17 172	91.03 143	64.12 148	96.03 51	68.39 246	90.14 118	91.50 183

CPTT-MVS		83.73 94	83.33 102	84.92 105	93.28 49	70.86 74	92.09 37	90.38 155	68.75 278	79.57 164	92.83 90	60.60 210	93.04 197	80.92 104	91.56 95	90.86 205

h-mvs33		83.15 112	82.19 120	86.02 72	90.56 101	70.85 75	88.15 157	89.16 208	76.02 96	84.67 80	91.39 129	61.54 187	95.50 69	82.71 88	75.48 342	91.72 177

新几何1				83.42 173	93.13 56	70.71 76		85.48 297	57.43 405	81.80 131	91.98 107	63.28 154	92.27 228	64.60 277	92.99 72	87.27 330

test12				86.80 54	92.63 69	70.70 77		91.79 112		82.71 120		71.67 58	96.16 48		94.50 53	93.54 96

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	73.53 163	85.69 66	94.45 32	65.00 142	95.56 64	82.75 86	91.87 88	92.50 143

RE-MVS-def			85.48 69		93.06 60	70.63 78	91.88 39	92.27 85	73.53 163	85.69 66	94.45 32	63.87 150		82.75 86	91.87 88	92.50 143

HPM-MVS_fast		85.35 73	84.95 79	86.57 59	93.69 42	70.58 80	92.15 36	91.62 119	73.89 152	82.67 121	94.09 50	62.60 166	95.54 66	80.93 103	92.93 73	93.57 93

MSLP-MVS++		85.43 69	85.76 63	84.45 121	91.93 77	70.24 81	90.71 62	92.86 59	77.46 55	84.22 93	92.81 92	67.16 116	92.94 199	80.36 111	94.35 59	90.16 235

MVSFormer		82.85 118	82.05 124	85.24 90	87.35 226	70.21 82	90.50 67	90.38 155	68.55 281	81.32 137	89.47 184	61.68 184	93.46 169	78.98 123	90.26 116	92.05 167

lupinMVS		81.39 147	80.27 155	84.76 112	87.35 226	70.21 82	85.55 244	86.41 282	62.85 354	81.32 137	88.61 211	61.68 184	92.24 230	78.41 130	90.26 116	91.83 170

xiu_mvs_v1_base_debu		80.80 161	79.72 170	84.03 152	87.35 226	70.19 84	85.56 241	88.77 225	69.06 271	81.83 128	88.16 225	50.91 305	92.85 202	78.29 132	87.56 160	89.06 276

xiu_mvs_v1_base		80.80 161	79.72 170	84.03 152	87.35 226	70.19 84	85.56 241	88.77 225	69.06 271	81.83 128	88.16 225	50.91 305	92.85 202	78.29 132	87.56 160	89.06 276

xiu_mvs_v1_base_debi		80.80 161	79.72 170	84.03 152	87.35 226	70.19 84	85.56 241	88.77 225	69.06 271	81.83 128	88.16 225	50.91 305	92.85 202	78.29 132	87.56 160	89.06 276

API-MVS		81.99 130	81.23 134	84.26 134	90.94 93	70.18 87	91.10 58	89.32 197	71.51 201	78.66 181	88.28 221	65.26 137	95.10 93	64.74 276	91.23 100	87.51 323

test_fmvsm_n_1920		85.29 74	85.34 71	85.13 95	86.12 266	69.93 88	88.65 137	90.78 144	69.97 246	88.27 32	93.98 59	71.39 62	91.54 258	88.49 32	90.45 113	93.91 68

OpenMVS	72.83 10	79.77 188	78.33 204	84.09 143	85.17 289	69.91 89	90.57 64	90.97 138	66.70 302	72.17 320	91.91 108	54.70 261	93.96 138	61.81 303	90.95 105	88.41 305

jason		81.39 147	80.29 154	84.70 114	86.63 256	69.90 90	85.95 231	86.77 277	63.24 347	81.07 143	89.47 184	61.08 200	92.15 232	78.33 131	90.07 121	92.05 167
jason: jason.
MVP-Stereo		76.12 277	74.46 287	81.13 249	85.37 285	69.79 91	84.42 277	87.95 248	65.03 327	67.46 369	85.33 304	53.28 276	91.73 249	58.01 339	83.27 242	81.85 411
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
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 83

PVSNet_Blended_VisFu		82.62 120	81.83 129	84.96 101	90.80 97	69.76 93	88.74 133	91.70 116	69.39 258	78.96 174	88.46 216	65.47 136	94.87 103	74.42 176	88.57 147	90.24 233

test_prior				86.33 60	92.61 70	69.59 94		92.97 55					95.48 70			93.91 68

APD-MVS_3200maxsize		85.97 56	85.88 59	86.22 63	92.69 68	69.53 95	91.93 38	92.99 50	73.54 162	85.94 62	94.51 30	65.80 134	95.61 63	83.04 82	92.51 79	93.53 97

test_fmvsmconf_n		85.92 57	86.04 57	85.57 82	85.03 296	69.51 96	89.62 92	90.58 148	73.42 166	87.75 44	94.02 54	72.85 44	93.24 178	90.37 7	90.75 108	93.96 65

EPNet		83.72 95	82.92 109	86.14 68	84.22 312	69.48 97	91.05 59	85.27 298	81.30 6	76.83 226	91.65 118	66.09 129	95.56 64	76.00 159	93.85 64	93.38 100
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ET-MVSNet_ETH3D		78.63 220	76.63 252	84.64 115	86.73 252	69.47 98	85.01 258	84.61 307	69.54 256	66.51 386	86.59 272	50.16 315	91.75 247	76.26 155	84.24 221	92.69 135

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	91.46 127	70.32 75	93.78 152	81.51 96	88.95 139	94.63 33

DP-MVS		76.78 265	74.57 283	83.42 173	93.29 48	69.46 100	88.55 141	83.70 320	63.98 343	70.20 338	88.89 203	54.01 269	94.80 107	46.66 409	81.88 260	86.01 358

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	91.23 132	73.28 37	93.91 146	81.50 97	88.80 142	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	91.23 132	73.28 37	93.91 146	81.50 97	88.80 142	94.77 25

test_fmvsmconf0.1_n		85.61 65	85.65 65	85.50 83	82.99 345	69.39 103	89.65 89	90.29 162	73.31 169	87.77 43	94.15 48	71.72 56	93.23 179	90.31 8	90.67 110	93.89 71

test_fmvsmvis_n_1920		84.02 89	83.87 91	84.49 120	84.12 314	69.37 104	88.15 157	87.96 247	70.01 244	83.95 100	93.23 79	68.80 97	91.51 261	88.61 29	89.96 122	92.57 138

nrg030		83.88 90	83.53 97	84.96 101	86.77 251	69.28 105	90.46 70	92.67 68	74.79 128	82.95 114	91.33 131	72.70 46	93.09 192	80.79 107	79.28 292	92.50 143

test_fmvsmconf0.01_n		84.73 83	84.52 85	85.34 87	80.25 387	69.03 106	89.47 95	89.65 182	73.24 173	86.98 56	94.27 41	66.62 119	93.23 179	90.26 9	89.95 123	93.78 80

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 35

XVG-OURS		80.41 175	79.23 184	83.97 157	85.64 276	69.02 108	83.03 310	90.39 154	71.09 211	77.63 208	91.49 126	54.62 263	91.35 267	75.71 161	83.47 238	91.54 181

PCF-MVS	73.52 7	80.38 177	78.84 193	85.01 99	87.71 217	68.99 109	83.65 291	91.46 127	63.00 351	77.77 206	90.28 159	66.10 128	95.09 94	61.40 306	88.22 154	90.94 203
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
QAPM		80.88 155	79.50 176	85.03 98	88.01 202	68.97 110	91.59 46	92.00 100	66.63 308	75.15 275	92.16 104	57.70 233	95.45 71	63.52 282	88.76 144	90.66 214

AdaColmap		80.58 173	79.42 177	84.06 147	93.09 59	68.91 111	89.36 103	88.97 219	69.27 262	75.70 253	89.69 175	57.20 241	95.77 60	63.06 287	88.41 152	87.50 324

fmvsm_l_conf0.5_n		84.47 84	84.54 83	84.27 132	85.42 283	68.81 112	88.49 142	87.26 266	68.08 288	88.03 38	93.49 70	72.04 52	91.77 246	88.90 26	89.14 138	92.24 157

原ACMM1				84.35 125	93.01 62	68.79 113		92.44 78	63.96 344	81.09 142	91.57 123	66.06 130	95.45 71	67.19 256	94.82 46	88.81 291

XVG-OURS-SEG-HR		80.81 158	79.76 169	83.96 158	85.60 278	68.78 114	83.54 297	90.50 151	70.66 226	76.71 230	91.66 117	60.69 205	91.26 270	76.94 147	81.58 262	91.83 170

LPG-MVS_test		82.08 127	81.27 133	84.50 118	89.23 148	68.76 115	90.22 76	91.94 104	75.37 109	76.64 232	91.51 124	54.29 264	94.91 98	78.44 128	83.78 226	89.83 256

LGP-MVS_train				84.50 118	89.23 148	68.76 115		91.94 104	75.37 109	76.64 232	91.51 124	54.29 264	94.91 98	78.44 128	83.78 226	89.83 256

Effi-MVS+-dtu		80.03 185	78.57 197	84.42 122	85.13 293	68.74 117	88.77 129	88.10 241	74.99 119	74.97 281	83.49 348	57.27 239	93.36 173	73.53 184	80.88 270	91.18 192

Vis-MVSNet		83.46 104	82.80 111	85.43 85	90.25 108	68.74 117	90.30 75	90.13 167	76.33 91	80.87 146	92.89 88	61.00 201	94.20 130	72.45 203	90.97 104	93.35 103
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
HQP_MVS		83.64 98	83.14 103	85.14 92	90.08 112	68.71 119	91.25 55	92.44 78	79.12 28	78.92 176	91.00 145	60.42 212	95.38 78	78.71 126	86.32 182	91.33 188

plane_prior						68.71 119	90.38 73		77.62 47						86.16 186

plane_prior6					89.84 121	68.70 121						60.42 212

ACMP	74.13 6	81.51 146	80.57 146	84.36 124	89.42 135	68.69 122	89.97 80	91.50 126	74.46 136	75.04 279	90.41 155	53.82 270	94.54 116	77.56 139	82.91 246	89.86 255
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
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	85.71 292	69.32 87	95.38 78	80.82 105	91.37 98	92.72 132

plane_prior3						68.60 124			78.44 36	78.92 176

CHOSEN 1792x2688		77.63 250	75.69 263	83.44 172	89.98 118	68.58 125	78.70 367	87.50 260	56.38 410	75.80 252	86.84 260	58.67 225	91.40 266	61.58 305	85.75 197	90.34 228

fmvsm_l_conf0.5_n_3		86.02 52	86.32 47	85.14 92	87.20 235	68.54 126	89.57 93	90.44 153	75.31 111	87.49 48	94.39 37	72.86 43	92.72 207	89.04 24	90.56 111	94.16 55

plane_prior7					90.08 112	68.51 127

GDP-MVS		83.52 102	82.64 113	86.16 65	88.14 193	68.45 128	89.13 114	92.69 66	72.82 181	83.71 104	91.86 112	55.69 251	95.35 82	80.03 114	89.74 127	94.69 28

fmvsm_l_conf0.5_n_a		84.13 87	84.16 88	84.06 147	85.38 284	68.40 129	88.34 149	86.85 276	67.48 295	87.48 49	93.40 75	70.89 68	91.61 251	88.38 34	89.22 136	92.16 164

ACMM	73.20 8	80.78 165	79.84 167	83.58 169	89.31 143	68.37 130	89.99 79	91.60 120	70.28 238	77.25 215	89.66 177	53.37 275	93.53 165	74.24 179	82.85 247	88.85 289
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs4		74.03 306	71.91 317	80.39 265	81.96 363	68.32 131	81.45 325	82.14 346	59.32 386	69.87 347	85.13 310	52.40 282	88.13 331	60.21 316	74.74 357	84.73 381

NP-MVS					89.62 125	68.32 131					90.24 161

mamba_0404		81.91 131	80.84 142	85.13 95	89.24 147	68.26 133	87.84 170	89.25 203	71.06 213	80.62 150	90.39 156	59.57 217	94.65 114	72.45 203	87.19 168	92.47 146

test222					91.50 82	68.26 133	84.16 282	83.20 332	54.63 416	79.74 161	91.63 120	58.97 222			91.42 96	86.77 344

Elysia		81.53 142	80.16 157	85.62 79	85.51 280	68.25 135	88.84 126	92.19 92	71.31 204	80.50 152	89.83 169	46.89 345	94.82 104	76.85 148	89.57 129	93.80 78

StellarMVS		81.53 142	80.16 157	85.62 79	85.51 280	68.25 135	88.84 126	92.19 92	71.31 204	80.50 152	89.83 169	46.89 345	94.82 104	76.85 148	89.57 129	93.80 78

CDS-MVSNet		79.07 209	77.70 224	83.17 185	87.60 221	68.23 137	84.40 278	86.20 287	67.49 294	76.36 240	86.54 276	61.54 187	90.79 284	61.86 302	87.33 165	90.49 222
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PS-MVSNAJ		81.69 137	81.02 138	83.70 165	89.51 130	68.21 138	84.28 280	90.09 168	70.79 220	81.26 141	85.62 297	63.15 160	94.29 124	75.62 163	88.87 141	88.59 300

fmvsm_s_conf0.5_n_a		83.63 99	83.41 99	84.28 130	86.14 265	68.12 139	89.43 97	82.87 339	70.27 239	87.27 53	93.80 66	69.09 90	91.58 253	88.21 35	83.65 233	93.14 116

UGNet		80.83 157	79.59 174	84.54 117	88.04 199	68.09 140	89.42 99	88.16 239	76.95 70	76.22 243	89.46 186	49.30 328	93.94 141	68.48 244	90.31 114	91.60 178
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
fmvsm_s_conf0.1_n_a		83.32 109	82.99 107	84.28 130	83.79 322	68.07 141	89.34 104	82.85 340	69.80 250	87.36 52	94.06 52	68.34 103	91.56 256	87.95 36	83.46 239	93.21 110

UA-Net		85.08 78	84.96 78	85.45 84	92.07 75	68.07 141	89.78 85	90.86 143	82.48 2	84.60 85	93.20 80	69.35 86	95.22 84	71.39 211	90.88 107	93.07 118

xiu_mvs_v2_base		81.69 137	81.05 137	83.60 167	89.15 151	68.03 143	84.46 274	90.02 169	70.67 223	81.30 140	86.53 277	63.17 159	94.19 132	75.60 164	88.54 148	88.57 301

LuminaMVS		80.68 166	79.62 173	83.83 161	85.07 295	68.01 144	86.99 195	88.83 222	70.36 234	81.38 136	87.99 232	50.11 316	92.51 217	79.02 120	86.89 174	90.97 201

mamba_0408		79.37 202	77.52 229	84.93 104	88.81 163	67.96 145	65.03 441	88.66 231	70.96 217	79.48 166	89.80 171	58.69 223	94.65 114	70.35 222	85.93 192	92.18 160

mamba_test_0407_2		77.67 249	77.52 229	78.12 314	88.81 163	67.96 145	65.03 441	88.66 231	70.96 217	79.48 166	89.80 171	58.69 223	74.23 434	70.35 222	85.93 192	92.18 160

mamba_test_0407		81.58 141	80.48 149	84.87 107	88.81 163	67.96 145	87.37 182	89.25 203	71.06 213	79.48 166	90.39 156	59.57 217	94.48 121	72.45 203	85.93 192	92.18 160

DELS-MVS		85.41 70	85.30 74	85.77 75	88.49 178	67.93 148	85.52 248	93.44 28	78.70 34	83.63 108	89.03 196	74.57 24	95.71 62	80.26 113	94.04 63	93.66 84
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_s_conf0.5_n_9		87.39 30	87.95 20	85.70 77	89.48 133	67.88 149	88.59 139	89.05 213	80.19 12	90.70 17	95.40 15	74.56 25	93.92 145	91.54 2	92.07 85	95.31 5

BP-MVS1		84.32 85	83.71 94	86.17 64	87.84 209	67.85 150	89.38 102	89.64 183	77.73 45	83.98 99	92.12 106	56.89 244	95.43 73	84.03 73	91.75 91	95.24 7

EI-MVSNet-Vis-set		84.19 86	83.81 92	85.31 88	88.18 190	67.85 150	87.66 173	89.73 180	80.05 15	82.95 114	89.59 181	70.74 71	94.82 104	80.66 110	84.72 210	93.28 106

PLC	70.83 11	78.05 236	76.37 258	83.08 190	91.88 79	67.80 152	88.19 154	89.46 189	64.33 336	69.87 347	88.38 218	53.66 271	93.58 160	58.86 329	82.73 249	87.86 315
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TAMVS		78.89 215	77.51 231	83.03 193	87.80 211	67.79 153	84.72 264	85.05 303	67.63 291	76.75 229	87.70 237	62.25 174	90.82 283	58.53 333	87.13 169	90.49 222

CLD-MVS		82.31 124	81.65 130	84.29 129	88.47 179	67.73 154	85.81 238	92.35 83	75.78 99	78.33 191	86.58 274	64.01 149	94.35 123	76.05 158	87.48 163	90.79 207
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
hse-mvs2		81.72 135	80.94 140	84.07 145	88.72 171	67.68 155	85.87 234	87.26 266	76.02 96	84.67 80	88.22 224	61.54 187	93.48 167	82.71 88	73.44 370	91.06 196

MVSMamba_PlusPlus		85.99 54	85.96 58	86.05 69	91.09 88	67.64 156	89.63 91	92.65 71	72.89 180	84.64 83	91.71 115	71.85 53	96.03 51	84.77 62	94.45 56	94.49 41

balanced_conf03		86.78 39	86.99 37	86.15 66	91.24 86	67.61 157	90.51 65	92.90 57	77.26 59	87.44 50	91.63 120	71.27 64	96.06 50	85.62 53	95.01 37	94.78 24

AUN-MVS		79.21 205	77.60 227	84.05 150	88.71 172	67.61 157	85.84 236	87.26 266	69.08 270	77.23 217	88.14 229	53.20 277	93.47 168	75.50 166	73.45 369	91.06 196

CS-MVS		86.69 41	86.95 39	85.90 74	90.76 99	67.57 159	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

KinetiMVS		83.31 110	82.61 114	85.39 86	87.08 243	67.56 160	88.06 159	91.65 117	77.80 44	82.21 124	91.79 113	57.27 239	94.07 136	77.77 137	89.89 125	94.56 38

EI-MVSNet-UG-set		83.81 91	83.38 100	85.09 97	87.87 207	67.53 161	87.44 181	89.66 181	79.74 18	82.23 123	89.41 190	70.24 77	94.74 109	79.95 115	83.92 225	92.99 126

Effi-MVS+		83.62 100	83.08 104	85.24 90	88.38 184	67.45 162	88.89 122	89.15 209	75.50 105	82.27 122	88.28 221	69.61 84	94.45 122	77.81 136	87.84 157	93.84 74

EG-PatchMatch MVS		74.04 304	71.82 318	80.71 259	84.92 297	67.42 163	85.86 235	88.08 242	66.04 314	64.22 401	83.85 336	35.10 419	92.56 213	57.44 343	80.83 271	82.16 410

OMC-MVS		82.69 119	81.97 127	84.85 108	88.75 170	67.42 163	87.98 161	90.87 142	74.92 123	79.72 162	91.65 118	62.19 176	93.96 138	75.26 169	86.42 181	93.16 114

fmvsm_s_conf0.5_n_5		85.22 75	85.55 67	84.25 135	86.26 260	67.40 165	89.18 108	89.31 198	72.50 182	88.31 31	93.86 63	69.66 83	91.96 238	89.81 11	91.05 102	93.38 100

PatchMatch-RL		72.38 326	70.90 330	76.80 336	88.60 175	67.38 166	79.53 353	76.17 407	62.75 357	69.36 352	82.00 374	45.51 363	84.89 368	53.62 369	80.58 275	78.12 425

LS3D		76.95 262	74.82 280	83.37 176	90.45 103	67.36 167	89.15 113	86.94 273	61.87 367	69.52 350	90.61 151	51.71 298	94.53 117	46.38 412	86.71 177	88.21 309

fmvsm_s_conf0.5_n		83.80 92	83.71 94	84.07 145	86.69 254	67.31 168	89.46 96	83.07 334	71.09 211	86.96 57	93.70 68	69.02 95	91.47 263	88.79 27	84.62 212	93.44 99

fmvsm_s_conf0.1_n		83.56 101	83.38 100	84.10 139	84.86 298	67.28 169	89.40 101	83.01 335	70.67 223	87.08 54	93.96 60	68.38 102	91.45 264	88.56 31	84.50 213	93.56 94

PS-MVSNAJss		82.07 128	81.31 132	84.34 126	86.51 258	67.27 170	89.27 105	91.51 123	71.75 194	79.37 169	90.22 163	63.15 160	94.27 126	77.69 138	82.36 254	91.49 184

114514_t		80.68 166	79.51 175	84.20 136	94.09 38	67.27 170	89.64 90	91.11 136	58.75 394	74.08 294	90.72 149	58.10 229	95.04 95	69.70 231	89.42 133	90.30 231

mvsmamba		80.60 170	79.38 178	84.27 132	89.74 124	67.24 172	87.47 178	86.95 272	70.02 243	75.38 263	88.93 201	51.24 302	92.56 213	75.47 167	89.22 136	93.00 125

casdiffmvs_mvg		85.99 54	86.09 56	85.70 77	87.65 220	67.22 173	88.69 135	93.04 42	79.64 21	85.33 69	92.54 97	73.30 36	94.50 119	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
SPE-MVS-test		86.29 50	86.48 45	85.71 76	91.02 91	67.21 174	92.36 30	93.78 19	78.97 33	83.51 109	91.20 135	70.65 73	95.15 87	81.96 94	94.89 42	94.77 25

anonymousdsp		78.60 221	77.15 237	82.98 196	80.51 385	67.08 175	87.24 188	89.53 187	65.66 319	75.16 274	87.19 254	52.52 279	92.25 229	77.17 144	79.34 291	89.61 263

MVS		78.19 232	76.99 241	81.78 229	85.66 275	66.99 176	84.66 266	90.47 152	55.08 415	72.02 322	85.27 305	63.83 151	94.11 135	66.10 264	89.80 126	84.24 385

HQP5-MVS						66.98 177

HQP-MVS		82.61 121	82.02 125	84.37 123	89.33 140	66.98 177	89.17 109	92.19 92	76.41 85	77.23 217	90.23 162	60.17 215	95.11 90	77.47 140	85.99 190	91.03 198

Fast-Effi-MVS+-dtu		78.02 237	76.49 253	82.62 214	83.16 339	66.96 179	86.94 198	87.45 262	72.45 183	71.49 328	84.17 332	54.79 260	91.58 253	67.61 250	80.31 279	89.30 272

F-COLMAP		76.38 275	74.33 289	82.50 217	89.28 145	66.95 180	88.41 144	89.03 214	64.05 341	66.83 378	88.61 211	46.78 347	92.89 201	57.48 342	78.55 296	87.67 318

HyFIR lowres test		77.53 251	75.40 271	83.94 159	89.59 126	66.62 181	80.36 343	88.64 234	56.29 411	76.45 237	85.17 309	57.64 234	93.28 175	61.34 308	83.10 245	91.91 169

ACMH	67.68 16	75.89 281	73.93 293	81.77 230	88.71 172	66.61 182	88.62 138	89.01 216	69.81 249	66.78 379	86.70 268	41.95 389	91.51 261	55.64 358	78.14 303	87.17 332
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
jajsoiax		79.29 203	77.96 211	83.27 179	84.68 303	66.57 183	89.25 106	90.16 166	69.20 267	75.46 259	89.49 183	45.75 361	93.13 190	76.84 150	80.80 272	90.11 239

VDD-MVS		83.01 117	82.36 118	84.96 101	91.02 91	66.40 184	88.91 121	88.11 240	77.57 49	84.39 89	93.29 78	52.19 285	93.91 146	77.05 146	88.70 146	94.57 37

mvs_tets		79.13 207	77.77 221	83.22 183	84.70 302	66.37 185	89.17 109	90.19 165	69.38 259	75.40 262	89.46 186	44.17 373	93.15 188	76.78 152	80.70 274	90.14 236

PAPM_NR		83.02 116	82.41 116	84.82 109	92.47 72	66.37 185	87.93 165	91.80 111	73.82 153	77.32 214	90.66 150	67.90 108	94.90 100	70.37 221	89.48 132	93.19 113

EC-MVSNet		86.01 53	86.38 46	84.91 106	89.31 143	66.27 187	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	93.01 124

pmmvs-eth3d		70.50 346	67.83 360	78.52 307	77.37 411	66.18 188	81.82 318	81.51 354	58.90 391	63.90 405	80.42 386	42.69 382	86.28 351	58.56 332	65.30 409	83.11 399

IB-MVS	68.01 15	75.85 282	73.36 302	83.31 177	84.76 301	66.03 189	83.38 299	85.06 302	70.21 241	69.40 351	81.05 378	45.76 360	94.66 113	65.10 273	75.49 341	89.25 273
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
MS-PatchMatch		73.83 307	72.67 309	77.30 331	83.87 321	66.02 190	81.82 318	84.66 306	61.37 371	68.61 359	82.82 361	47.29 340	88.21 329	59.27 323	84.32 220	77.68 426

FE-MVS		77.78 243	75.68 264	84.08 144	88.09 197	66.00 191	83.13 305	87.79 253	68.42 285	78.01 199	85.23 307	45.50 364	95.12 88	59.11 326	85.83 196	91.11 194

test_0402		72.79 324	70.44 335	79.84 278	88.13 194	65.99 192	85.93 232	84.29 312	65.57 320	67.40 372	85.49 300	46.92 344	92.61 209	35.88 437	74.38 360	80.94 416

BH-RMVSNet		79.61 190	78.44 200	83.14 186	89.38 139	65.93 193	84.95 260	87.15 269	73.56 161	78.19 194	89.79 173	56.67 246	93.36 173	59.53 322	86.74 176	90.13 237

BH-untuned		79.47 195	78.60 196	82.05 224	89.19 150	65.91 194	86.07 229	88.52 236	72.18 188	75.42 261	87.69 238	61.15 198	93.54 164	60.38 314	86.83 175	86.70 346

cascas		76.72 266	74.64 282	82.99 195	85.78 273	65.88 195	82.33 314	89.21 206	60.85 373	72.74 310	81.02 379	47.28 341	93.75 156	67.48 252	85.02 205	89.34 271

fmvsm_s_conf0.5_n_4		85.39 71	85.75 64	84.30 128	86.70 253	65.83 196	88.77 129	89.78 176	75.46 106	88.35 30	93.73 67	69.19 89	93.06 194	91.30 3	88.44 151	94.02 63

patch_mono-2		83.65 97	84.54 83	80.99 252	90.06 116	65.83 196	84.21 281	88.74 229	71.60 199	85.01 72	92.44 98	74.51 26	83.50 378	82.15 93	92.15 83	93.64 90

MSDG		73.36 315	70.99 329	80.49 264	84.51 308	65.80 198	80.71 337	86.13 289	65.70 318	65.46 392	83.74 340	44.60 368	90.91 282	51.13 383	76.89 317	84.74 380

旧先验1					91.96 76	65.79 199		86.37 284			93.08 85	69.31 88			92.74 76	88.74 296

casdiffmvs		85.11 77	85.14 76	85.01 99	87.20 235	65.77 200	87.75 171	92.83 61	77.84 43	84.36 92	92.38 99	72.15 50	93.93 144	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
mamv4		76.81 264	78.23 208	72.54 381	86.12 266	65.75 201	78.76 366	82.07 348	64.12 338	72.97 308	91.02 144	67.97 106	68.08 446	83.04 82	78.02 304	83.80 392

COLMAP_ROB	66.92 17	73.01 321	70.41 336	80.81 257	87.13 238	65.63 202	88.30 151	84.19 315	62.96 352	63.80 406	87.69 238	38.04 409	92.56 213	46.66 409	74.91 355	84.24 385
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
fmvsm_s_conf0.5_n_8		86.56 44	87.17 35	84.73 113	87.76 216	65.62 203	89.20 107	92.21 90	79.94 17	89.74 22	94.86 22	68.63 99	94.20 130	90.83 5	91.39 97	94.38 46

EIA-MVS		83.31 110	82.80 111	84.82 109	89.59 126	65.59 204	88.21 153	92.68 67	74.66 132	78.96 174	86.42 279	69.06 92	95.26 83	75.54 165	90.09 119	93.62 91

v7n		78.97 212	77.58 228	83.14 186	83.45 330	65.51 205	88.32 150	91.21 131	73.69 157	72.41 316	86.32 282	57.93 230	93.81 151	69.18 236	75.65 338	90.11 239

V42		79.38 201	78.24 206	82.83 202	81.10 379	65.50 206	85.55 244	89.82 175	71.57 200	78.21 193	86.12 286	60.66 207	93.18 187	75.64 162	75.46 344	89.81 258

PVSNet_BlendedMVS		80.60 170	80.02 161	82.36 220	88.85 159	65.40 207	86.16 227	92.00 100	69.34 260	78.11 196	86.09 287	66.02 131	94.27 126	71.52 208	82.06 257	87.39 325

PVSNet_Blended		80.98 153	80.34 152	82.90 199	88.85 159	65.40 207	84.43 276	92.00 100	67.62 292	78.11 196	85.05 313	66.02 131	94.27 126	71.52 208	89.50 131	89.01 281

baseline		84.93 80	84.98 77	84.80 111	87.30 233	65.39 209	87.30 186	92.88 58	77.62 47	84.04 98	92.26 101	71.81 54	93.96 138	81.31 99	90.30 115	95.03 11

test_djsdf		80.30 180	79.32 181	83.27 179	83.98 318	65.37 210	90.50 67	90.38 155	68.55 281	76.19 244	88.70 207	56.44 248	93.46 169	78.98 123	80.14 282	90.97 201

ACMH+	68.96 14	76.01 280	74.01 291	82.03 225	88.60 175	65.31 211	88.86 123	87.55 258	70.25 240	67.75 365	87.47 246	41.27 391	93.19 186	58.37 335	75.94 335	87.60 320

fmvsm_s_conf0.5_n_3		86.36 49	87.46 29	83.09 188	87.08 243	65.21 212	89.09 116	90.21 164	79.67 19	89.98 19	95.02 20	73.17 39	91.71 250	91.30 3	91.60 92	92.34 150

CR-MVSNet		73.37 313	71.27 326	79.67 283	81.32 377	65.19 213	75.92 392	80.30 371	59.92 381	72.73 311	81.19 376	52.50 280	86.69 345	59.84 318	77.71 307	87.11 336

RPMNet		73.51 311	70.49 334	82.58 216	81.32 377	65.19 213	75.92 392	92.27 85	57.60 403	72.73 311	76.45 418	52.30 283	95.43 73	48.14 404	77.71 307	87.11 336

fmvsm_s_conf0.5_n_7		83.34 108	84.03 90	81.28 243	85.73 274	65.13 215	85.40 249	89.90 174	74.96 122	82.13 125	93.89 62	66.65 118	87.92 333	86.56 47	91.05 102	90.80 206

fmvsm_s_conf0.5_n_6		85.55 66	86.20 50	83.60 167	87.32 232	65.13 215	88.86 123	91.63 118	75.41 107	88.23 34	93.45 74	68.56 100	92.47 218	89.52 16	92.78 75	93.20 112

BH-w/o		78.21 230	77.33 235	80.84 256	88.81 163	65.13 215	84.87 261	87.85 252	69.75 253	74.52 289	84.74 319	61.34 193	93.11 191	58.24 337	85.84 195	84.27 384

thisisatest0530		79.40 199	77.76 222	84.31 127	87.69 219	65.10 218	87.36 183	84.26 314	70.04 242	77.42 211	88.26 223	49.94 319	94.79 108	70.20 224	84.70 211	93.03 122

FA-MVS(test-final)		80.96 154	79.91 164	84.10 139	88.30 187	65.01 219	84.55 271	90.01 170	73.25 172	79.61 163	87.57 241	58.35 228	94.72 110	71.29 212	86.25 184	92.56 139

fmvsm_s_conf0.5_n_2		84.04 88	84.11 89	83.81 163	86.17 264	65.00 220	86.96 196	87.28 264	74.35 138	88.25 33	94.23 44	61.82 182	92.60 210	89.85 10	88.09 156	93.84 74

v10		79.74 189	78.67 194	82.97 197	84.06 316	64.95 221	87.88 168	90.62 147	73.11 174	75.11 276	86.56 275	61.46 190	94.05 137	73.68 182	75.55 340	89.90 253

fmvsm_s_conf0.1_n_2		83.80 92	83.79 93	83.83 161	85.62 277	64.94 222	87.03 193	86.62 280	74.32 139	87.97 41	94.33 38	60.67 206	92.60 210	89.72 12	87.79 158	93.96 65

SDMVSNet		80.38 177	80.18 156	80.99 252	89.03 157	64.94 222	80.45 342	89.40 190	75.19 115	76.61 234	89.98 165	60.61 209	87.69 337	76.83 151	83.55 235	90.33 229

dcpmvs_2		85.63 64	86.15 54	84.06 147	91.71 80	64.94 222	86.47 216	91.87 108	73.63 158	86.60 60	93.02 86	76.57 15	91.87 244	83.36 77	92.15 83	95.35 3

IterMVS-SCA-FT		75.43 288	73.87 295	80.11 273	82.69 352	64.85 225	81.57 323	83.47 325	69.16 268	70.49 335	84.15 333	51.95 292	88.15 330	69.23 235	72.14 380	87.34 327

MVSTER		79.01 210	77.88 216	82.38 219	83.07 340	64.80 226	84.08 285	88.95 220	69.01 274	78.69 179	87.17 255	54.70 261	92.43 220	74.69 172	80.57 276	89.89 254

Anonymous20240529		80.19 183	78.89 192	84.10 139	90.60 100	64.75 227	88.95 120	90.90 140	65.97 316	80.59 151	91.17 137	49.97 318	93.73 158	69.16 237	82.70 251	93.81 76

XVG-ACMP-BASELINE		76.11 278	74.27 290	81.62 232	83.20 336	64.67 228	83.60 294	89.75 179	69.75 253	71.85 323	87.09 257	32.78 423	92.11 233	69.99 228	80.43 278	88.09 311

viewmanbaseed2359cas		83.66 96	83.55 96	84.00 155	86.81 249	64.53 229	86.65 210	91.75 115	74.89 124	83.15 113	91.68 116	68.74 98	92.83 205	79.02 120	89.24 135	94.63 33

v1192		79.59 192	78.43 201	83.07 191	83.55 328	64.52 230	86.93 199	90.58 148	70.83 219	77.78 205	85.90 288	59.15 221	93.94 141	73.96 181	77.19 314	90.76 209

Fast-Effi-MVS+		80.81 158	79.92 163	83.47 171	88.85 159	64.51 231	85.53 246	89.39 191	70.79 220	78.49 186	85.06 312	67.54 111	93.58 160	67.03 259	86.58 178	92.32 152

v1144		80.03 185	79.03 188	83.01 194	83.78 323	64.51 231	87.11 191	90.57 150	71.96 193	78.08 198	86.20 284	61.41 191	93.94 141	74.93 171	77.23 312	90.60 217

v8		79.97 187	79.02 189	82.80 205	84.09 315	64.50 233	87.96 162	90.29 162	74.13 147	75.24 272	86.81 261	62.88 165	93.89 149	74.39 177	75.40 347	90.00 247

EPP-MVSNet		83.40 106	83.02 106	84.57 116	90.13 110	64.47 234	92.32 31	90.73 145	74.45 137	79.35 170	91.10 138	69.05 93	95.12 88	72.78 194	87.22 167	94.13 57

GeoE		81.71 136	81.01 139	83.80 164	89.51 130	64.45 235	88.97 119	88.73 230	71.27 207	78.63 182	89.76 174	66.32 125	93.20 184	69.89 229	86.02 189	93.74 81

UniMVSNet (Re)		81.60 140	81.11 136	83.09 188	88.38 184	64.41 236	87.60 174	93.02 46	78.42 37	78.56 184	88.16 225	69.78 81	93.26 177	69.58 233	76.49 324	91.60 178

LTVRE_ROB	69.57 13	76.25 276	74.54 285	81.41 238	88.60 175	64.38 237	79.24 357	89.12 212	70.76 222	69.79 349	87.86 234	49.09 331	93.20 184	56.21 357	80.16 280	86.65 347
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
Anonymous20231211		78.97 212	77.69 225	82.81 204	90.54 102	64.29 238	90.11 78	91.51 123	65.01 328	76.16 248	88.13 230	50.56 310	93.03 198	69.68 232	77.56 311	91.11 194

testdata				79.97 275	90.90 94	64.21 239		84.71 305	59.27 387	85.40 68	92.91 87	62.02 179	89.08 315	68.95 239	91.37 98	86.63 348

v2v482		80.23 181	79.29 182	83.05 192	83.62 326	64.14 240	87.04 192	89.97 171	73.61 159	78.18 195	87.22 252	61.10 199	93.82 150	76.11 156	76.78 321	91.18 192

VDDNet		81.52 144	80.67 144	84.05 150	90.44 104	64.13 241	89.73 87	85.91 291	71.11 210	83.18 111	93.48 71	50.54 311	93.49 166	73.40 187	88.25 153	94.54 40

PAPR		81.66 139	80.89 141	83.99 156	90.27 107	64.00 242	86.76 207	91.77 114	68.84 277	77.13 224	89.50 182	67.63 110	94.88 102	67.55 251	88.52 149	93.09 117

AstraMVS		80.81 158	80.14 159	82.80 205	86.05 269	63.96 243	86.46 217	85.90 292	73.71 156	80.85 147	90.56 152	54.06 268	91.57 255	79.72 118	83.97 224	92.86 129

v144192		79.47 195	78.37 202	82.78 209	83.35 331	63.96 243	86.96 196	90.36 158	69.99 245	77.50 209	85.67 295	60.66 207	93.77 154	74.27 178	76.58 322	90.62 215

v1921920		79.22 204	78.03 210	82.80 205	83.30 333	63.94 245	86.80 203	90.33 159	69.91 248	77.48 210	85.53 299	58.44 227	93.75 156	73.60 183	76.85 319	90.71 213

guyue		81.13 151	80.64 145	82.60 215	86.52 257	63.92 246	86.69 209	87.73 255	73.97 148	80.83 148	89.69 175	56.70 245	91.33 269	78.26 135	85.40 203	92.54 140

tttt0517		79.40 199	77.91 213	83.90 160	88.10 196	63.84 247	88.37 148	84.05 316	71.45 202	76.78 228	89.12 193	49.93 321	94.89 101	70.18 225	83.18 244	92.96 127

thisisatest0515		77.33 255	75.38 272	83.18 184	85.27 288	63.80 248	82.11 317	83.27 328	65.06 326	75.91 249	83.84 337	49.54 323	94.27 126	67.24 255	86.19 185	91.48 185

diffmvs		82.10 126	81.88 128	82.76 211	83.00 343	63.78 249	83.68 290	89.76 178	72.94 178	82.02 127	89.85 168	65.96 133	90.79 284	82.38 92	87.30 166	93.71 82
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_yl		81.17 149	80.47 150	83.24 181	89.13 152	63.62 250	86.21 225	89.95 172	72.43 186	81.78 132	89.61 179	57.50 236	93.58 160	70.75 216	86.90 172	92.52 141

DCV-MVSNet		81.17 149	80.47 150	83.24 181	89.13 152	63.62 250	86.21 225	89.95 172	72.43 186	81.78 132	89.61 179	57.50 236	93.58 160	70.75 216	86.90 172	92.52 141

AllTest		70.96 339	68.09 354	79.58 285	85.15 291	63.62 250	84.58 270	79.83 376	62.31 361	60.32 418	86.73 262	32.02 424	88.96 319	50.28 388	71.57 384	86.15 354

TestCases				79.58 285	85.15 291	63.62 250		79.83 376	62.31 361	60.32 418	86.73 262	32.02 424	88.96 319	50.28 388	71.57 384	86.15 354

icg_test_0407_2		78.92 214	78.93 191	78.90 297	87.13 238	63.59 254	76.58 388	89.33 193	70.51 229	77.82 202	89.03 196	61.84 180	81.38 393	72.56 199	85.56 199	91.74 173

icg_test_0407		80.61 168	79.90 165	82.75 212	87.13 238	63.59 254	85.33 250	89.33 193	70.51 229	77.82 202	89.03 196	61.84 180	92.91 200	72.56 199	85.56 199	91.74 173

ICG_test_0404		77.16 258	76.42 256	79.37 288	87.13 238	63.59 254	77.12 386	89.33 193	70.51 229	66.22 389	89.03 196	50.36 313	82.78 383	72.56 199	85.56 199	91.74 173

icg_test_0403		80.80 161	80.12 160	82.87 201	87.13 238	63.59 254	85.19 251	89.33 193	70.51 229	78.49 186	89.03 196	63.26 156	93.27 176	72.56 199	85.56 199	91.74 173

v1240		78.99 211	77.78 220	82.64 213	83.21 335	63.54 258	86.62 212	90.30 161	69.74 255	77.33 213	85.68 294	57.04 242	93.76 155	73.13 191	76.92 316	90.62 215

CHOSEN 280x420		66.51 379	64.71 381	71.90 384	81.45 372	63.52 259	57.98 448	68.95 431	53.57 418	62.59 411	76.70 416	46.22 354	75.29 430	55.25 359	79.68 285	76.88 428

IterMVS		74.29 299	72.94 307	78.35 310	81.53 371	63.49 260	81.58 322	82.49 343	68.06 289	69.99 344	83.69 343	51.66 299	85.54 360	65.85 267	71.64 383	86.01 358
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet_NR-MVSNet		81.88 132	81.54 131	82.92 198	88.46 180	63.46 261	87.13 189	92.37 82	80.19 12	78.38 189	89.14 192	71.66 59	93.05 195	70.05 226	76.46 325	92.25 155

DU-MVS		81.12 152	80.52 148	82.90 199	87.80 211	63.46 261	87.02 194	91.87 108	79.01 31	78.38 189	89.07 194	65.02 140	93.05 195	70.05 226	76.46 325	92.20 158

LFMVS		81.82 134	81.23 134	83.57 170	91.89 78	63.43 263	89.84 81	81.85 351	77.04 69	83.21 110	93.10 81	52.26 284	93.43 171	71.98 206	89.95 123	93.85 72

NR-MVSNet		80.23 181	79.38 178	82.78 209	87.80 211	63.34 264	86.31 222	91.09 137	79.01 31	72.17 320	89.07 194	67.20 115	92.81 206	66.08 265	75.65 338	92.20 158

IS-MVSNet		83.15 112	82.81 110	84.18 137	89.94 119	63.30 265	91.59 46	88.46 237	79.04 30	79.49 165	92.16 104	65.10 139	94.28 125	67.71 249	91.86 90	94.95 12

TR-MVS		77.44 252	76.18 259	81.20 246	88.24 188	63.24 266	84.61 269	86.40 283	67.55 293	77.81 204	86.48 278	54.10 266	93.15 188	57.75 341	82.72 250	87.20 331

MVS_Test		83.15 112	83.06 105	83.41 175	86.86 246	63.21 267	86.11 228	92.00 100	74.31 140	82.87 116	89.44 189	70.03 78	93.21 181	77.39 142	88.50 150	93.81 76

IterMVS-LS		80.06 184	79.38 178	82.11 223	85.89 270	63.20 268	86.79 204	89.34 192	74.19 144	75.45 260	86.72 264	66.62 119	92.39 222	72.58 196	76.86 318	90.75 210
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		80.52 174	79.98 162	82.12 221	84.28 310	63.19 269	86.41 218	88.95 220	74.18 145	78.69 179	87.54 244	66.62 119	92.43 220	72.57 197	80.57 276	90.74 211

CANet_DTU		80.61 168	79.87 166	82.83 202	85.60 278	63.17 270	87.36 183	88.65 233	76.37 89	75.88 250	88.44 217	53.51 273	93.07 193	73.30 188	89.74 127	92.25 155

MGCFI-Net		85.06 79	85.51 68	83.70 165	89.42 135	63.01 271	89.43 97	92.62 74	76.43 84	87.53 47	91.34 130	72.82 45	93.42 172	81.28 100	88.74 145	94.66 32

GBi-Net		78.40 225	77.40 232	81.40 239	87.60 221	63.01 271	88.39 145	89.28 199	71.63 196	75.34 265	87.28 248	54.80 257	91.11 273	62.72 289	79.57 286	90.09 241

test1		78.40 225	77.40 232	81.40 239	87.60 221	63.01 271	88.39 145	89.28 199	71.63 196	75.34 265	87.28 248	54.80 257	91.11 273	62.72 289	79.57 286	90.09 241

FMVSNet1		77.44 252	76.12 260	81.40 239	86.81 249	63.01 271	88.39 145	89.28 199	70.49 233	74.39 291	87.28 248	49.06 332	91.11 273	60.91 310	78.52 297	90.09 241

TAPA-MVS	73.13 9	79.15 206	77.94 212	82.79 208	89.59 126	62.99 275	88.16 156	91.51 123	65.77 317	77.14 223	91.09 139	60.91 202	93.21 181	50.26 390	87.05 170	92.17 163
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
RRT-MVS		82.60 123	82.10 122	84.10 139	87.98 203	62.94 276	87.45 180	91.27 129	77.42 56	79.85 160	90.28 159	56.62 247	94.70 112	79.87 117	88.15 155	94.67 29

FMVSNet2		78.20 231	77.21 236	81.20 246	87.60 221	62.89 277	87.47 178	89.02 215	71.63 196	75.29 271	87.28 248	54.80 257	91.10 276	62.38 294	79.38 290	89.61 263

VortexMVS		78.57 223	77.89 215	80.59 261	85.89 270	62.76 278	85.61 239	89.62 184	72.06 191	74.99 280	85.38 303	55.94 250	90.77 286	74.99 170	76.58 322	88.23 307

GA-MVS		76.87 263	75.17 277	81.97 227	82.75 350	62.58 279	81.44 326	86.35 285	72.16 190	74.74 284	82.89 359	46.20 355	92.02 236	68.85 241	81.09 267	91.30 190

D2MVS		74.82 295	73.21 303	79.64 284	79.81 394	62.56 280	80.34 344	87.35 263	64.37 335	68.86 356	82.66 363	46.37 351	90.10 294	67.91 248	81.24 265	86.25 351

viewmambaseed2359dif		80.41 175	79.84 167	82.12 221	82.95 347	62.50 281	83.39 298	88.06 244	67.11 297	80.98 144	90.31 158	66.20 127	91.01 280	74.62 173	84.90 207	92.86 129

FMVSNet3		77.88 241	76.85 244	80.97 254	86.84 248	62.36 282	86.52 215	88.77 225	71.13 209	75.34 265	86.66 270	54.07 267	91.10 276	62.72 289	79.57 286	89.45 267

TranMVSNet+NR-MVSNet		80.84 156	80.31 153	82.42 218	87.85 208	62.33 283	87.74 172	91.33 128	80.55 9	77.99 200	89.86 167	65.23 138	92.62 208	67.05 258	75.24 352	92.30 153

1314		76.53 268	75.30 275	80.21 271	83.93 319	62.32 284	84.66 266	88.81 223	60.23 378	70.16 341	84.07 334	55.30 254	90.73 287	67.37 253	83.21 243	87.59 322

MG-MVS		83.41 105	83.45 98	83.28 178	92.74 67	62.28 285	88.17 155	89.50 188	75.22 112	81.49 135	92.74 96	66.75 117	95.11 90	72.85 193	91.58 94	92.45 147

SCA		74.22 301	72.33 314	79.91 276	84.05 317	62.17 286	79.96 350	79.29 383	66.30 311	72.38 317	80.13 391	51.95 292	88.60 325	59.25 324	77.67 310	88.96 285

PMMVS		69.34 358	68.67 347	71.35 390	75.67 417	62.03 287	75.17 398	73.46 417	50.00 428	68.68 357	79.05 400	52.07 290	78.13 406	61.16 309	82.77 248	73.90 432

eth_miper_zixun_eth		77.92 240	76.69 250	81.61 234	83.00 343	61.98 288	83.15 304	89.20 207	69.52 257	74.86 283	84.35 326	61.76 183	92.56 213	71.50 210	72.89 374	90.28 232

v148		78.72 218	77.80 219	81.47 236	82.73 351	61.96 289	86.30 223	88.08 242	73.26 171	76.18 245	85.47 301	62.46 170	92.36 224	71.92 207	73.82 366	90.09 241

PAPM		77.68 248	76.40 257	81.51 235	87.29 234	61.85 290	83.78 287	89.59 185	64.74 330	71.23 330	88.70 207	62.59 167	93.66 159	52.66 374	87.03 171	89.01 281

cl22		78.07 235	77.01 239	81.23 245	82.37 360	61.83 291	83.55 295	87.98 246	68.96 275	75.06 278	83.87 335	61.40 192	91.88 243	73.53 184	76.39 327	89.98 250

baseline2		75.70 283	73.83 296	81.30 242	83.26 334	61.79 292	82.57 313	80.65 363	66.81 299	66.88 377	83.42 349	57.86 232	92.19 231	63.47 283	79.57 286	89.91 252

JIA-IIPM		66.32 381	62.82 393	76.82 335	77.09 412	61.72 293	65.34 439	75.38 408	58.04 400	64.51 399	62.32 440	42.05 388	86.51 348	51.45 381	69.22 395	82.21 408

miper_ehance_all_eth		78.59 222	77.76 222	81.08 250	82.66 353	61.56 294	83.65 291	89.15 209	68.87 276	75.55 256	83.79 339	66.49 122	92.03 235	73.25 189	76.39 327	89.64 262

c3_l		78.75 216	77.91 213	81.26 244	82.89 348	61.56 294	84.09 284	89.13 211	69.97 246	75.56 255	84.29 327	66.36 124	92.09 234	73.47 186	75.48 342	90.12 238

miper_enhance_ethall		77.87 242	76.86 243	80.92 255	81.65 367	61.38 296	82.68 311	88.98 217	65.52 321	75.47 257	82.30 368	65.76 135	92.00 237	72.95 192	76.39 327	89.39 269

mmtdpeth		74.16 302	73.01 306	77.60 327	83.72 325	61.13 297	85.10 256	85.10 301	72.06 191	77.21 221	80.33 388	43.84 375	85.75 356	77.14 145	52.61 436	85.91 361

ppachtmachnet_test		70.04 352	67.34 370	78.14 313	79.80 395	61.13 297	79.19 359	80.59 364	59.16 388	65.27 394	79.29 399	46.75 348	87.29 341	49.33 395	66.72 402	86.00 360

sc_t1		72.19 330	69.51 341	80.23 270	84.81 299	61.09 299	84.68 265	80.22 373	60.70 374	71.27 329	83.58 346	36.59 414	89.24 311	60.41 313	63.31 414	90.37 227

TDRefinement		67.49 371	64.34 382	76.92 334	73.47 430	61.07 300	84.86 262	82.98 337	59.77 382	58.30 425	85.13 310	26.06 434	87.89 334	47.92 406	60.59 422	81.81 412

VNet		82.21 125	82.41 116	81.62 232	90.82 96	60.93 301	84.47 272	89.78 176	76.36 90	84.07 97	91.88 110	64.71 143	90.26 291	70.68 218	88.89 140	93.66 84

ab-mvs		79.51 193	78.97 190	81.14 248	88.46 180	60.91 302	83.84 286	89.24 205	70.36 234	79.03 173	88.87 204	63.23 158	90.21 293	65.12 272	82.57 252	92.28 154

PatchmatchNet		73.12 319	71.33 325	78.49 308	83.18 337	60.85 303	79.63 352	78.57 388	64.13 337	71.73 324	79.81 396	51.20 303	85.97 355	57.40 344	76.36 332	88.66 297
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VPA-MVSNet		80.60 170	80.55 147	80.76 258	88.07 198	60.80 304	86.86 201	91.58 121	75.67 103	80.24 156	89.45 188	63.34 153	90.25 292	70.51 220	79.22 293	91.23 191

EGC-MVSNET		52.07 411	47.05 415	67.14 411	83.51 329	60.71 305	80.50 341	67.75 433	0.07 461	0.43 462	75.85 423	24.26 439	81.54 391	28.82 444	62.25 416	59.16 444

Anonymous202405211		78.25 228	77.01 239	81.99 226	91.03 90	60.67 306	84.77 263	83.90 318	70.65 227	80.00 159	91.20 135	41.08 393	91.43 265	65.21 271	85.26 204	93.85 72

ITE_SJBPF				78.22 311	81.77 366	60.57 307		83.30 327	69.25 264	67.54 367	87.20 253	36.33 416	87.28 342	54.34 365	74.62 358	86.80 343

MDA-MVSNet-bldmvs		66.68 377	63.66 387	75.75 342	79.28 402	60.56 308	73.92 408	78.35 390	64.43 333	50.13 440	79.87 395	44.02 374	83.67 375	46.10 414	56.86 426	83.03 401

cl____		77.72 245	76.76 247	80.58 262	82.49 357	60.48 309	83.09 306	87.87 250	69.22 265	74.38 292	85.22 308	62.10 177	91.53 259	71.09 213	75.41 346	89.73 261

DIV-MVS_self_test		77.72 245	76.76 247	80.58 262	82.48 358	60.48 309	83.09 306	87.86 251	69.22 265	74.38 292	85.24 306	62.10 177	91.53 259	71.09 213	75.40 347	89.74 260

1112_ss		77.40 254	76.43 255	80.32 268	89.11 156	60.41 311	83.65 291	87.72 256	62.13 364	73.05 307	86.72 264	62.58 168	89.97 297	62.11 300	80.80 272	90.59 218

tt0805		78.73 217	77.83 217	81.43 237	85.17 289	60.30 312	89.41 100	90.90 140	71.21 208	77.17 222	88.73 206	46.38 350	93.21 181	72.57 197	78.96 294	90.79 207

UniMVSNet_ETH3D		79.10 208	78.24 206	81.70 231	86.85 247	60.24 313	87.28 187	88.79 224	74.25 143	76.84 225	90.53 154	49.48 324	91.56 256	67.98 247	82.15 255	93.29 105

HY-MVS	69.67 12	77.95 239	77.15 237	80.36 266	87.57 225	60.21 314	83.37 300	87.78 254	66.11 312	75.37 264	87.06 259	63.27 155	90.48 290	61.38 307	82.43 253	90.40 226

sd_testset		77.70 247	77.40 232	78.60 302	89.03 157	60.02 315	79.00 362	85.83 293	75.19 115	76.61 234	89.98 165	54.81 256	85.46 362	62.63 293	83.55 235	90.33 229

RPSCF		73.23 318	71.46 322	78.54 305	82.50 356	59.85 316	82.18 316	82.84 341	58.96 390	71.15 332	89.41 190	45.48 365	84.77 369	58.82 330	71.83 382	91.02 200

test_cas_vis1_n_1920		73.76 308	73.74 297	73.81 369	75.90 415	59.77 317	80.51 340	82.40 344	58.30 396	81.62 134	85.69 293	44.35 372	76.41 418	76.29 154	78.61 295	85.23 371

dmvs_re		71.14 337	70.58 332	72.80 378	81.96 363	59.68 318	75.60 396	79.34 382	68.55 281	69.27 354	80.72 384	49.42 325	76.54 415	52.56 375	77.79 306	82.19 409

miper_lstm_enhance		74.11 303	73.11 305	77.13 333	80.11 389	59.62 319	72.23 412	86.92 275	66.76 301	70.40 336	82.92 358	56.93 243	82.92 382	69.06 238	72.63 375	88.87 288

OurMVSNet-221017-0		74.26 300	72.42 313	79.80 279	83.76 324	59.59 320	85.92 233	86.64 278	66.39 310	66.96 376	87.58 240	39.46 399	91.60 252	65.76 268	69.27 394	88.22 308

Patchmatch-RL test		70.24 349	67.78 362	77.61 325	77.43 410	59.57 321	71.16 416	70.33 424	62.94 353	68.65 358	72.77 430	50.62 309	85.49 361	69.58 233	66.58 404	87.77 317

tt0320-xc		70.11 351	67.45 368	78.07 316	85.33 286	59.51 322	83.28 301	78.96 386	58.77 392	67.10 375	80.28 389	36.73 413	87.42 340	56.83 352	59.77 424	87.29 329

OpenMVS_ROB	64.09 19	70.56 345	68.19 351	77.65 324	80.26 386	59.41 323	85.01 258	82.96 338	58.76 393	65.43 393	82.33 367	37.63 411	91.23 272	45.34 419	76.03 334	82.32 407

tt0320		70.49 347	68.03 355	77.89 318	84.78 300	59.12 324	83.55 295	80.44 368	58.13 398	67.43 371	80.41 387	39.26 401	87.54 339	55.12 360	63.18 415	86.99 339

our_test_3		69.14 359	67.00 372	75.57 345	79.80 395	58.80 325	77.96 378	77.81 392	59.55 384	62.90 410	78.25 409	47.43 339	83.97 373	51.71 378	67.58 401	83.93 390

ADS-MVSNet2		66.20 384	63.33 388	74.82 357	79.92 391	58.75 326	67.55 431	75.19 409	53.37 419	65.25 395	75.86 421	42.32 384	80.53 398	41.57 427	68.91 396	85.18 372

pm-mvs1		77.25 257	76.68 251	78.93 296	84.22 312	58.62 327	86.41 218	88.36 238	71.37 203	73.31 303	88.01 231	61.22 197	89.15 314	64.24 280	73.01 373	89.03 280

MonoMVSNet		76.49 272	75.80 261	78.58 303	81.55 370	58.45 328	86.36 221	86.22 286	74.87 127	74.73 285	83.73 341	51.79 297	88.73 322	70.78 215	72.15 379	88.55 302

WR-MVS		79.49 194	79.22 185	80.27 269	88.79 168	58.35 329	85.06 257	88.61 235	78.56 35	77.65 207	88.34 219	63.81 152	90.66 288	64.98 274	77.22 313	91.80 172

FIs		82.07 128	82.42 115	81.04 251	88.80 167	58.34 330	88.26 152	93.49 27	76.93 71	78.47 188	91.04 141	69.92 80	92.34 226	69.87 230	84.97 206	92.44 148

CostFormer		75.24 292	73.90 294	79.27 290	82.65 354	58.27 331	80.80 332	82.73 342	61.57 368	75.33 269	83.13 354	55.52 252	91.07 279	64.98 274	78.34 302	88.45 303

Test_1112_low_res		76.40 274	75.44 269	79.27 290	89.28 145	58.09 332	81.69 321	87.07 270	59.53 385	72.48 315	86.67 269	61.30 194	89.33 308	60.81 312	80.15 281	90.41 225

tfpnnormal		74.39 298	73.16 304	78.08 315	86.10 268	58.05 333	84.65 268	87.53 259	70.32 237	71.22 331	85.63 296	54.97 255	89.86 298	43.03 423	75.02 354	86.32 350

test-LLR		72.94 323	72.43 312	74.48 360	81.35 375	58.04 334	78.38 371	77.46 395	66.66 303	69.95 345	79.00 402	48.06 337	79.24 401	66.13 262	84.83 208	86.15 354

test-mter		71.41 335	70.39 337	74.48 360	81.35 375	58.04 334	78.38 371	77.46 395	60.32 377	69.95 345	79.00 402	36.08 417	79.24 401	66.13 262	84.83 208	86.15 354

mvs_anonymous		79.42 198	79.11 187	80.34 267	84.45 309	57.97 336	82.59 312	87.62 257	67.40 296	76.17 247	88.56 214	68.47 101	89.59 304	70.65 219	86.05 188	93.47 98

tpm cat1		70.57 344	68.31 350	77.35 330	82.41 359	57.95 337	78.08 376	80.22 373	52.04 422	68.54 360	77.66 413	52.00 291	87.84 335	51.77 377	72.07 381	86.25 351

SixPastTwentyTwo		73.37 313	71.26 327	79.70 281	85.08 294	57.89 338	85.57 240	83.56 323	71.03 215	65.66 391	85.88 289	42.10 387	92.57 212	59.11 326	63.34 413	88.65 298

thres200		75.55 285	74.47 286	78.82 298	87.78 214	57.85 339	83.07 308	83.51 324	72.44 185	75.84 251	84.42 322	52.08 289	91.75 247	47.41 407	83.64 234	86.86 342

XXY-MVS		75.41 289	75.56 267	74.96 354	83.59 327	57.82 340	80.59 339	83.87 319	66.54 309	74.93 282	88.31 220	63.24 157	80.09 399	62.16 298	76.85 319	86.97 340

reproduce_monomvs		75.40 290	74.38 288	78.46 309	83.92 320	57.80 341	83.78 287	86.94 273	73.47 165	72.25 319	84.47 321	38.74 404	89.27 310	75.32 168	70.53 389	88.31 306

K. test v3		71.19 336	68.51 348	79.21 292	83.04 342	57.78 342	84.35 279	76.91 402	72.90 179	62.99 409	82.86 360	39.27 400	91.09 278	61.65 304	52.66 435	88.75 294

tfpn200view9		76.42 273	75.37 273	79.55 287	89.13 152	57.65 343	85.17 252	83.60 321	73.41 167	76.45 237	86.39 280	52.12 286	91.95 239	48.33 400	83.75 229	89.07 274

thres400		76.50 269	75.37 273	79.86 277	89.13 152	57.65 343	85.17 252	83.60 321	73.41 167	76.45 237	86.39 280	52.12 286	91.95 239	48.33 400	83.75 229	90.00 247

CMPMVS	51.72 21	70.19 350	68.16 352	76.28 338	73.15 433	57.55 345	79.47 354	83.92 317	48.02 431	56.48 431	84.81 317	43.13 379	86.42 350	62.67 292	81.81 261	84.89 378
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs6		74.69 296	73.39 300	78.61 301	81.38 374	57.48 346	86.64 211	87.95 248	64.99 329	70.18 339	86.61 271	50.43 312	89.52 305	62.12 299	70.18 391	88.83 290

test_vis1_n_1920		75.52 286	75.78 262	74.75 359	79.84 393	57.44 347	83.26 302	85.52 296	62.83 355	79.34 171	86.17 285	45.10 366	79.71 400	78.75 125	81.21 266	87.10 338

PVSNet_0	57.27 20	61.67 396	59.27 399	68.85 403	79.61 398	57.44 347	68.01 429	73.44 418	55.93 412	58.54 424	70.41 435	44.58 369	77.55 410	47.01 408	35.91 447	71.55 435

thres600view7		76.50 269	75.44 269	79.68 282	89.40 137	57.16 349	85.53 246	83.23 329	73.79 154	76.26 242	87.09 257	51.89 294	91.89 242	48.05 405	83.72 232	90.00 247

lessismore_v0				78.97 295	81.01 380	57.15 350		65.99 437		61.16 415	82.82 361	39.12 402	91.34 268	59.67 320	46.92 442	88.43 304

TransMVSNet (Re)		75.39 291	74.56 284	77.86 319	85.50 282	57.10 351	86.78 205	86.09 290	72.17 189	71.53 327	87.34 247	63.01 164	89.31 309	56.84 351	61.83 417	87.17 332

thres100view900		76.50 269	75.55 268	79.33 289	89.52 129	56.99 352	85.83 237	83.23 329	73.94 150	76.32 241	87.12 256	51.89 294	91.95 239	48.33 400	83.75 229	89.07 274

TESTMET0.1,1		69.89 354	69.00 346	72.55 380	79.27 403	56.85 353	78.38 371	74.71 414	57.64 402	68.09 363	77.19 415	37.75 410	76.70 414	63.92 281	84.09 223	84.10 388

WTY-MVS		75.65 284	75.68 264	75.57 345	86.40 259	56.82 354	77.92 380	82.40 344	65.10 325	76.18 245	87.72 236	63.13 163	80.90 396	60.31 315	81.96 258	89.00 283

MDA-MVSNet_test_wron		65.03 386	62.92 390	71.37 388	75.93 414	56.73 355	69.09 428	74.73 413	57.28 406	54.03 435	77.89 410	45.88 357	74.39 433	49.89 392	61.55 418	82.99 402

pmmvs3		57.79 400	54.26 405	68.37 406	64.02 448	56.72 356	75.12 401	65.17 439	40.20 440	52.93 436	69.86 436	20.36 445	75.48 427	45.45 418	55.25 433	72.90 434

tpm2		73.26 317	71.46 322	78.63 300	83.34 332	56.71 357	80.65 338	80.40 370	56.63 409	73.55 301	82.02 373	51.80 296	91.24 271	56.35 356	78.42 300	87.95 312

TinyColmap		67.30 374	64.81 380	74.76 358	81.92 365	56.68 358	80.29 345	81.49 355	60.33 376	56.27 432	83.22 351	24.77 438	87.66 338	45.52 417	69.47 393	79.95 421

YYNet1		65.03 386	62.91 391	71.38 387	75.85 416	56.60 359	69.12 427	74.66 415	57.28 406	54.12 434	77.87 411	45.85 358	74.48 432	49.95 391	61.52 419	83.05 400

PM-MVS		66.41 380	64.14 383	73.20 375	73.92 425	56.45 360	78.97 363	64.96 441	63.88 345	64.72 398	80.24 390	19.84 446	83.44 379	66.24 261	64.52 411	79.71 422

PVSNet	64.34 18	72.08 332	70.87 331	75.69 343	86.21 262	56.44 361	74.37 406	80.73 362	62.06 365	70.17 340	82.23 370	42.86 381	83.31 380	54.77 363	84.45 217	87.32 328

pmmvs5		71.55 334	70.20 339	75.61 344	77.83 408	56.39 362	81.74 320	80.89 359	57.76 401	67.46 369	84.49 320	49.26 329	85.32 364	57.08 347	75.29 350	85.11 375

testing11		75.14 293	74.01 291	78.53 306	88.16 191	56.38 363	80.74 336	80.42 369	70.67 223	72.69 313	83.72 342	43.61 377	89.86 298	62.29 296	83.76 228	89.36 270

WR-MVS_H		78.51 224	78.49 198	78.56 304	88.02 200	56.38 363	88.43 143	92.67 68	77.14 64	73.89 296	87.55 243	66.25 126	89.24 311	58.92 328	73.55 368	90.06 245

MIMVSNet		70.69 343	69.30 342	74.88 356	84.52 307	56.35 365	75.87 394	79.42 380	64.59 331	67.76 364	82.41 365	41.10 392	81.54 391	46.64 411	81.34 263	86.75 345

USDC		70.33 348	68.37 349	76.21 339	80.60 383	56.23 366	79.19 359	86.49 281	60.89 372	61.29 414	85.47 301	31.78 426	89.47 307	53.37 371	76.21 333	82.94 403

Baseline_NR-MVSNet		78.15 233	78.33 204	77.61 325	85.79 272	56.21 367	86.78 205	85.76 294	73.60 160	77.93 201	87.57 241	65.02 140	88.99 316	67.14 257	75.33 349	87.63 319

tpmvs		71.09 338	69.29 343	76.49 337	82.04 362	56.04 368	78.92 364	81.37 357	64.05 341	67.18 374	78.28 408	49.74 322	89.77 300	49.67 393	72.37 376	83.67 393

FC-MVSNet-test		81.52 144	82.02 125	80.03 274	88.42 183	55.97 369	87.95 163	93.42 30	77.10 67	77.38 212	90.98 147	69.96 79	91.79 245	68.46 245	84.50 213	92.33 151

testing91		76.54 267	75.66 266	79.18 293	88.43 182	55.89 370	81.08 329	83.00 336	73.76 155	75.34 265	84.29 327	46.20 355	90.07 295	64.33 278	84.50 213	91.58 180

mvs5depth		69.45 357	67.45 368	75.46 349	73.93 424	55.83 371	79.19 359	83.23 329	66.89 298	71.63 326	83.32 350	33.69 422	85.09 365	59.81 319	55.34 432	85.46 367

GG-mvs-BLEND				75.38 350	81.59 369	55.80 372	79.32 356	69.63 427		67.19 373	73.67 428	43.24 378	88.90 321	50.41 385	84.50 213	81.45 413

VPNet		78.69 219	78.66 195	78.76 299	88.31 186	55.72 373	84.45 275	86.63 279	76.79 75	78.26 192	90.55 153	59.30 220	89.70 303	66.63 260	77.05 315	90.88 204

baseline1		76.98 261	76.75 249	77.66 323	88.13 194	55.66 374	85.12 255	81.89 349	73.04 176	76.79 227	88.90 202	62.43 171	87.78 336	63.30 286	71.18 386	89.55 265

test_vis1_rt		60.28 397	58.42 400	65.84 414	67.25 443	55.60 375	70.44 421	60.94 447	44.33 436	59.00 422	66.64 437	24.91 437	68.67 444	62.80 288	69.48 392	73.25 433

testing99		76.09 279	75.12 278	79.00 294	88.16 191	55.50 376	80.79 333	81.40 356	73.30 170	75.17 273	84.27 330	44.48 370	90.02 296	64.28 279	84.22 222	91.48 185

testing222		74.04 304	72.66 310	78.19 312	87.89 206	55.36 377	81.06 330	79.20 384	71.30 206	74.65 287	83.57 347	39.11 403	88.67 324	51.43 382	85.75 197	90.53 220

FMVSNet5		69.50 356	67.96 356	74.15 365	82.97 346	55.35 378	80.01 349	82.12 347	62.56 359	63.02 407	81.53 375	36.92 412	81.92 389	48.42 399	74.06 362	85.17 374

test_fmvs1_n		70.86 341	70.24 338	72.73 379	72.51 437	55.28 379	81.27 328	79.71 378	51.49 426	78.73 178	84.87 315	27.54 433	77.02 412	76.06 157	79.97 284	85.88 362

test_vis1_n		69.85 355	69.21 344	71.77 385	72.66 436	55.27 380	81.48 324	76.21 406	52.03 423	75.30 270	83.20 353	28.97 431	76.22 420	74.60 174	78.41 301	83.81 391

test_fmvs1		70.93 340	70.52 333	72.16 383	73.71 426	55.05 381	80.82 331	78.77 387	51.21 427	78.58 183	84.41 323	31.20 428	76.94 413	75.88 160	80.12 283	84.47 383

sss		73.60 310	73.64 298	73.51 371	82.80 349	55.01 382	76.12 390	81.69 352	62.47 360	74.68 286	85.85 291	57.32 238	78.11 407	60.86 311	80.93 268	87.39 325

mvsany_test1		62.30 394	61.26 398	65.41 415	69.52 439	54.86 383	66.86 433	49.78 455	46.65 432	68.50 361	83.21 352	49.15 330	66.28 447	56.93 350	60.77 420	75.11 431

ECVR-MVS		79.61 190	79.26 183	80.67 260	90.08 112	54.69 384	87.89 167	77.44 397	74.88 125	80.27 155	92.79 93	48.96 334	92.45 219	68.55 243	92.50 80	94.86 19

EPNet_dtu		75.46 287	74.86 279	77.23 332	82.57 355	54.60 385	86.89 200	83.09 333	71.64 195	66.25 388	85.86 290	55.99 249	88.04 332	54.92 362	86.55 179	89.05 279
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CP-MVSNet		78.22 229	78.34 203	77.84 320	87.83 210	54.54 386	87.94 164	91.17 133	77.65 46	73.48 302	88.49 215	62.24 175	88.43 327	62.19 297	74.07 361	90.55 219

gg-mvs-nofinetune		69.95 353	67.96 356	75.94 340	83.07 340	54.51 387	77.23 385	70.29 425	63.11 349	70.32 337	62.33 439	43.62 376	88.69 323	53.88 368	87.76 159	84.62 382

PS-CasMVS		78.01 238	78.09 209	77.77 322	87.71 217	54.39 388	88.02 160	91.22 130	77.50 54	73.26 304	88.64 210	60.73 203	88.41 328	61.88 301	73.88 365	90.53 220

Anonymous20240521		68.80 362	67.22 371	73.55 370	74.33 422	54.11 389	83.18 303	85.61 295	58.15 397	61.68 413	80.94 381	30.71 429	81.27 394	57.00 349	73.34 372	85.28 370

Patchmtry		70.74 342	69.16 345	75.49 348	80.72 381	54.07 390	74.94 403	80.30 371	58.34 395	70.01 342	81.19 376	52.50 280	86.54 347	53.37 371	71.09 387	85.87 363

PEN-MVS		77.73 244	77.69 225	77.84 320	87.07 245	53.91 391	87.91 166	91.18 132	77.56 51	73.14 306	88.82 205	61.23 196	89.17 313	59.95 317	72.37 376	90.43 224

gm-plane-assit					81.40 373	53.83 392			62.72 358		80.94 381		92.39 222	63.40 285

CL-MVSNet_self_test		72.37 327	71.46 322	75.09 353	79.49 400	53.53 393	80.76 335	85.01 304	69.12 269	70.51 334	82.05 372	57.92 231	84.13 372	52.27 376	66.00 407	87.60 320

MDTV_nov1_ep13			69.97 340		83.18 337	53.48 394	77.10 387	80.18 375	60.45 375	69.33 353	80.44 385	48.89 335	86.90 344	51.60 379	78.51 298

KD-MVS_2432*1600		66.22 382	63.89 385	73.21 373	75.47 420	53.42 395	70.76 419	84.35 310	64.10 339	66.52 384	78.52 406	34.55 420	84.98 366	50.40 386	50.33 439	81.23 414

miper_refine_blended		66.22 382	63.89 385	73.21 373	75.47 420	53.42 395	70.76 419	84.35 310	64.10 339	66.52 384	78.52 406	34.55 420	84.98 366	50.40 386	50.33 439	81.23 414

test1111		79.43 197	79.18 186	80.15 272	89.99 117	53.31 397	87.33 185	77.05 401	75.04 118	80.23 157	92.77 95	48.97 333	92.33 227	68.87 240	92.40 82	94.81 22

LF4IMVS		64.02 390	62.19 394	69.50 399	70.90 438	53.29 398	76.13 389	77.18 400	52.65 421	58.59 423	80.98 380	23.55 441	76.52 416	53.06 373	66.66 403	78.68 424

MVStest1		56.63 402	52.76 408	68.25 408	61.67 450	53.25 399	71.67 414	68.90 432	38.59 443	50.59 439	83.05 355	25.08 436	70.66 440	36.76 436	38.56 446	80.83 417

DTE-MVSNet		76.99 260	76.80 245	77.54 328	86.24 261	53.06 400	87.52 176	90.66 146	77.08 68	72.50 314	88.67 209	60.48 211	89.52 305	57.33 345	70.74 388	90.05 246

test2506		77.30 256	76.49 253	79.74 280	90.08 112	52.02 401	87.86 169	63.10 444	74.88 125	80.16 158	92.79 93	38.29 408	92.35 225	68.74 242	92.50 80	94.86 19

tpm		72.37 327	71.71 319	74.35 362	82.19 361	52.00 402	79.22 358	77.29 399	64.56 332	72.95 309	83.68 344	51.35 300	83.26 381	58.33 336	75.80 336	87.81 316

test_fmvs2		68.35 368	67.48 367	70.98 394	69.50 440	51.95 403	80.05 348	76.38 405	49.33 429	74.65 287	84.38 324	23.30 442	75.40 429	74.51 175	75.17 353	85.60 365

ETVMVS		72.25 329	71.05 328	75.84 341	87.77 215	51.91 404	79.39 355	74.98 410	69.26 263	73.71 298	82.95 357	40.82 395	86.14 352	46.17 413	84.43 218	89.47 266

WB-MVSnew		71.96 333	71.65 320	72.89 377	84.67 306	51.88 405	82.29 315	77.57 394	62.31 361	73.67 300	83.00 356	53.49 274	81.10 395	45.75 416	82.13 256	85.70 364

MIMVSNet1		68.58 364	66.78 374	73.98 367	80.07 390	51.82 406	80.77 334	84.37 309	64.40 334	59.75 421	82.16 371	36.47 415	83.63 376	42.73 424	70.33 390	86.48 349

Vis-MVSNet (Re-imp)		78.36 227	78.45 199	78.07 316	88.64 174	51.78 407	86.70 208	79.63 379	74.14 146	75.11 276	90.83 148	61.29 195	89.75 301	58.10 338	91.60 92	92.69 135

LCM-MVSNet-Re		77.05 259	76.94 242	77.36 329	87.20 235	51.60 408	80.06 347	80.46 367	75.20 114	67.69 366	86.72 264	62.48 169	88.98 317	63.44 284	89.25 134	91.51 182

Gipuma		45.18 418	41.86 421	55.16 430	77.03 413	51.52 409	32.50 454	80.52 365	32.46 450	27.12 453	35.02 454	9.52 457	75.50 426	22.31 451	60.21 423	38.45 453
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
UnsupCasMVSNet_eth		67.33 373	65.99 377	71.37 388	73.48 429	51.47 410	75.16 399	85.19 299	65.20 324	60.78 416	80.93 383	42.35 383	77.20 411	57.12 346	53.69 434	85.44 368

UnsupCasMVSNet_bld		63.70 391	61.53 397	70.21 397	73.69 427	51.39 411	72.82 410	81.89 349	55.63 413	57.81 427	71.80 432	38.67 405	78.61 404	49.26 396	52.21 437	80.63 418

UBG		73.08 320	72.27 315	75.51 347	88.02 200	51.29 412	78.35 374	77.38 398	65.52 321	73.87 297	82.36 366	45.55 362	86.48 349	55.02 361	84.39 219	88.75 294

FPMVS		53.68 407	51.64 409	59.81 422	65.08 446	51.03 413	69.48 424	69.58 428	41.46 439	40.67 446	72.32 431	16.46 450	70.00 443	24.24 450	65.42 408	58.40 446

WBMVS		73.43 312	72.81 308	75.28 351	87.91 205	50.99 414	78.59 370	81.31 358	65.51 323	74.47 290	84.83 316	46.39 349	86.68 346	58.41 334	77.86 305	88.17 310

CVMVSNet		72.99 322	72.58 311	74.25 364	84.28 310	50.85 415	86.41 218	83.45 326	44.56 435	73.23 305	87.54 244	49.38 326	85.70 357	65.90 266	78.44 299	86.19 353

Anonymous20231206		68.60 363	67.80 361	71.02 393	80.23 388	50.75 416	78.30 375	80.47 366	56.79 408	66.11 390	82.63 364	46.35 352	78.95 403	43.62 422	75.70 337	83.36 396

ambc				75.24 352	73.16 432	50.51 417	63.05 446	87.47 261		64.28 400	77.81 412	17.80 448	89.73 302	57.88 340	60.64 421	85.49 366

APD_test1		53.31 408	49.93 413	63.42 418	65.68 445	50.13 418	71.59 415	66.90 436	34.43 448	40.58 447	71.56 433	8.65 459	76.27 419	34.64 439	55.36 431	63.86 442

tpmrst		72.39 325	72.13 316	73.18 376	80.54 384	49.91 419	79.91 351	79.08 385	63.11 349	71.69 325	79.95 393	55.32 253	82.77 384	65.66 269	73.89 364	86.87 341

Patchmatch-test		64.82 388	63.24 389	69.57 398	79.42 401	49.82 420	63.49 445	69.05 430	51.98 424	59.95 420	80.13 391	50.91 305	70.98 439	40.66 429	73.57 367	87.90 314

EPMVS		69.02 360	68.16 352	71.59 386	79.61 398	49.80 421	77.40 383	66.93 435	62.82 356	70.01 342	79.05 400	45.79 359	77.86 409	56.58 354	75.26 351	87.13 335

SSC-MVS3.2		73.35 316	73.39 300	73.23 372	85.30 287	49.01 422	74.58 405	81.57 353	75.21 113	73.68 299	85.58 298	52.53 278	82.05 388	54.33 366	77.69 309	88.63 299

dp		66.80 376	65.43 378	70.90 395	79.74 397	48.82 423	75.12 401	74.77 412	59.61 383	64.08 403	77.23 414	42.89 380	80.72 397	48.86 398	66.58 404	83.16 398

UWE-MVS		72.13 331	71.49 321	74.03 366	86.66 255	47.70 424	81.40 327	76.89 403	63.60 346	75.59 254	84.22 331	39.94 398	85.62 359	48.98 397	86.13 187	88.77 293

test0.0.03 1		68.00 370	67.69 363	68.90 402	77.55 409	47.43 425	75.70 395	72.95 421	66.66 303	66.56 382	82.29 369	48.06 337	75.87 424	44.97 420	74.51 359	83.41 395

SD_0403		74.65 297	74.77 281	74.29 363	86.20 263	47.42 426	83.71 289	85.12 300	69.30 261	68.50 361	87.95 233	59.40 219	86.05 353	49.38 394	83.35 240	89.40 268

myMVS_eth3d28		73.62 309	73.53 299	73.90 368	88.20 189	47.41 427	78.06 377	79.37 381	74.29 142	73.98 295	84.29 327	44.67 367	83.54 377	51.47 380	87.39 164	90.74 211

ADS-MVSNet		64.36 389	62.88 392	68.78 404	79.92 391	47.17 428	67.55 431	71.18 423	53.37 419	65.25 395	75.86 421	42.32 384	73.99 435	41.57 427	68.91 396	85.18 372

EU-MVSNet		68.53 366	67.61 365	71.31 391	78.51 407	47.01 429	84.47 272	84.27 313	42.27 438	66.44 387	84.79 318	40.44 396	83.76 374	58.76 331	68.54 399	83.17 397

test_fmvs3		63.36 392	61.82 395	67.98 409	62.51 449	46.96 430	77.37 384	74.03 416	45.24 434	67.50 368	78.79 405	12.16 454	72.98 438	72.77 195	66.02 406	83.99 389

ttmdpeth		59.91 398	57.10 402	68.34 407	67.13 444	46.65 431	74.64 404	67.41 434	48.30 430	62.52 412	85.04 314	20.40 444	75.93 423	42.55 425	45.90 445	82.44 406

KD-MVS_self_test		68.81 361	67.59 366	72.46 382	74.29 423	45.45 432	77.93 379	87.00 271	63.12 348	63.99 404	78.99 404	42.32 384	84.77 369	56.55 355	64.09 412	87.16 334

testf1		45.72 415	41.96 419	57.00 424	56.90 452	45.32 433	66.14 436	59.26 449	26.19 452	30.89 451	60.96 443	4.14 462	70.64 441	26.39 448	46.73 443	55.04 447

APD_test2		45.72 415	41.96 419	57.00 424	56.90 452	45.32 433	66.14 436	59.26 449	26.19 452	30.89 451	60.96 443	4.14 462	70.64 441	26.39 448	46.73 443	55.04 447

LCM-MVSNet		54.25 404	49.68 414	67.97 410	53.73 458	45.28 435	66.85 434	80.78 361	35.96 447	39.45 448	62.23 441	8.70 458	78.06 408	48.24 403	51.20 438	80.57 419

test_vis3_rt		49.26 414	47.02 416	56.00 426	54.30 455	45.27 436	66.76 435	48.08 456	36.83 445	44.38 444	53.20 449	7.17 461	64.07 449	56.77 353	55.66 429	58.65 445

testing3-2		75.12 294	75.19 276	74.91 355	90.40 105	45.09 437	80.29 345	78.42 389	78.37 40	76.54 236	87.75 235	44.36 371	87.28 342	57.04 348	83.49 237	92.37 149

test20.03		67.45 372	66.95 373	68.94 401	75.48 419	44.84 438	77.50 382	77.67 393	66.66 303	63.01 408	83.80 338	47.02 343	78.40 405	42.53 426	68.86 398	83.58 394

mvsany_test3		53.99 405	51.45 410	61.61 420	55.51 454	44.74 439	63.52 444	45.41 459	43.69 437	58.11 426	76.45 418	17.99 447	63.76 450	54.77 363	47.59 441	76.34 429

PatchT		68.46 367	67.85 358	70.29 396	80.70 382	43.93 440	72.47 411	74.88 411	60.15 379	70.55 333	76.57 417	49.94 319	81.59 390	50.58 384	74.83 356	85.34 369

MVS-HIRNet		59.14 399	57.67 401	63.57 417	81.65 367	43.50 441	71.73 413	65.06 440	39.59 442	51.43 437	57.73 445	38.34 407	82.58 385	39.53 430	73.95 363	64.62 441

testing3		68.56 365	67.67 364	71.22 392	87.33 231	42.87 442	83.06 309	71.54 422	70.36 234	69.08 355	84.38 324	30.33 430	85.69 358	37.50 435	75.45 345	85.09 376

WAC-MVS						42.58 443								39.46 431

myMVS_eth3d		67.02 375	66.29 376	69.21 400	84.68 303	42.58 443	78.62 368	73.08 419	66.65 306	66.74 380	79.46 397	31.53 427	82.30 386	39.43 432	76.38 330	82.75 404

PMVS	37.38 22	44.16 419	40.28 423	55.82 428	40.82 463	42.54 445	65.12 440	63.99 443	34.43 448	24.48 454	57.12 447	3.92 464	76.17 421	17.10 455	55.52 430	48.75 449
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_f		52.09 410	50.82 411	55.90 427	53.82 457	42.31 446	59.42 447	58.31 451	36.45 446	56.12 433	70.96 434	12.18 453	57.79 453	53.51 370	56.57 428	67.60 438

testgi		66.67 378	66.53 375	67.08 412	75.62 418	41.69 447	75.93 391	76.50 404	66.11 312	65.20 397	86.59 272	35.72 418	74.71 431	43.71 421	73.38 371	84.84 379

Syy-MVS		68.05 369	67.85 358	68.67 405	84.68 303	40.97 448	78.62 368	73.08 419	66.65 306	66.74 380	79.46 397	52.11 288	82.30 386	32.89 440	76.38 330	82.75 404

ANet_high		50.57 413	46.10 417	63.99 416	48.67 461	39.13 449	70.99 418	80.85 360	61.39 370	31.18 450	57.70 446	17.02 449	73.65 437	31.22 443	15.89 458	79.18 423

UWE-MVS-28		65.32 385	64.93 379	66.49 413	78.70 405	38.55 450	77.86 381	64.39 442	62.00 366	64.13 402	83.60 345	41.44 390	76.00 422	31.39 442	80.89 269	84.92 377

MDTV_nov1_ep13_2view						37.79 451	75.16 399		55.10 414	66.53 383		49.34 327		53.98 367		87.94 313

DSMNet-mixed		57.77 401	56.90 403	60.38 421	67.70 442	35.61 452	69.18 425	53.97 453	32.30 451	57.49 428	79.88 394	40.39 397	68.57 445	38.78 433	72.37 376	76.97 427

MVE	26.22 23	30.37 425	25.89 429	43.81 436	44.55 462	35.46 453	28.87 455	39.07 460	18.20 456	18.58 458	40.18 453	2.68 465	47.37 458	17.07 456	23.78 455	48.60 450
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
new_pmnet		50.91 412	50.29 412	52.78 432	68.58 441	34.94 454	63.71 443	56.63 452	39.73 441	44.95 443	65.47 438	21.93 443	58.48 452	34.98 438	56.62 427	64.92 440

wuyk23d		16.82 428	15.94 431	19.46 442	58.74 451	31.45 455	39.22 452	3.74 467	6.84 458	6.04 461	2.70 461	1.27 466	24.29 461	10.54 461	14.40 460	2.63 458

E-PMN		31.77 422	30.64 425	35.15 439	52.87 459	27.67 456	57.09 449	47.86 457	24.64 454	16.40 459	33.05 455	11.23 455	54.90 455	14.46 458	18.15 456	22.87 455

kuosan		39.70 421	40.40 422	37.58 438	64.52 447	26.98 457	65.62 438	33.02 462	46.12 433	42.79 445	48.99 451	24.10 440	46.56 459	12.16 460	26.30 453	39.20 452

DeepMVS_CX				27.40 441	40.17 464	26.90 458		24.59 465	17.44 457	23.95 455	48.61 452	9.77 456	26.48 460	18.06 453	24.47 454	28.83 454

dongtai		45.42 417	45.38 418	45.55 435	73.36 431	26.85 459	67.72 430	34.19 461	54.15 417	49.65 441	56.41 448	25.43 435	62.94 451	19.45 452	28.09 452	46.86 451

EMVS		30.81 424	29.65 426	34.27 440	50.96 460	25.95 460	56.58 450	46.80 458	24.01 455	15.53 460	30.68 456	12.47 452	54.43 456	12.81 459	17.05 457	22.43 456

dmvs_testset		62.63 393	64.11 384	58.19 423	78.55 406	24.76 461	75.28 397	65.94 438	67.91 290	60.34 417	76.01 420	53.56 272	73.94 436	31.79 441	67.65 400	75.88 430

new-patchmatchnet		61.73 395	61.73 396	61.70 419	72.74 435	24.50 462	69.16 426	78.03 391	61.40 369	56.72 430	75.53 424	38.42 406	76.48 417	45.95 415	57.67 425	84.13 387

WB-MVS		54.94 403	54.72 404	55.60 429	73.50 428	20.90 463	74.27 407	61.19 446	59.16 388	50.61 438	74.15 426	47.19 342	75.78 425	17.31 454	35.07 448	70.12 436

SSC-MVS		53.88 406	53.59 406	54.75 431	72.87 434	19.59 464	73.84 409	60.53 448	57.58 404	49.18 442	73.45 429	46.34 353	75.47 428	16.20 457	32.28 450	69.20 437

PMMVS2		40.82 420	38.86 424	46.69 434	53.84 456	16.45 465	48.61 451	49.92 454	37.49 444	31.67 449	60.97 442	8.14 460	56.42 454	28.42 445	30.72 451	67.19 439

tmp_tt		18.61 427	21.40 430	10.23 443	4.82 466	10.11 466	34.70 453	30.74 464	1.48 460	23.91 456	26.07 457	28.42 432	13.41 462	27.12 446	15.35 459	7.17 457

N_pmnet		52.79 409	53.26 407	51.40 433	78.99 404	7.68 467	69.52 423	3.89 466	51.63 425	57.01 429	74.98 425	40.83 394	65.96 448	37.78 434	64.67 410	80.56 420

test_method		31.52 423	29.28 427	38.23 437	27.03 465	6.50 468	20.94 456	62.21 445	4.05 459	22.35 457	52.50 450	13.33 451	47.58 457	27.04 447	34.04 449	60.62 443

test123		6.12 430	8.11 433	0.14 444	0.06 468	0.09 469	71.05 417	0.03 469	0.04 463	0.25 464	1.30 463	0.05 467	0.03 464	0.21 463	0.01 462	0.29 459

testmvs		6.04 431	8.02 434	0.10 445	0.08 467	0.03 470	69.74 422	0.04 468	0.05 462	0.31 463	1.68 462	0.02 468	0.04 463	0.24 462	0.02 461	0.25 460

mmdepth		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

monomultidepth		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

test_blank		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

uanet_test		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

DCPMVS		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

cdsmvs_eth3d_5k		19.96 426	26.61 428	0.00 446	0.00 469	0.00 471	0.00 457	89.26 202	0.00 464	0.00 465	88.61 211	61.62 186	0.00 465	0.00 464	0.00 463	0.00 461

pcd_1.5k_mvsjas		5.26 432	7.02 435	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	63.15 160	0.00 465	0.00 464	0.00 463	0.00 461

sosnet-low-res		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

sosnet		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

uncertanet		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

Regformer		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

ab-mvs-re		7.23 429	9.64 432	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	86.72 264	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

uanet		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

PC_three_1452									68.21 287	92.02 12	94.00 56	82.09 5	95.98 57	84.58 64	96.68 2	94.95 12

eth-test2					0.00 469

eth-test					0.00 469

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 53

9.14			88.26 16		92.84 65		91.52 51	94.75 1	73.93 151	88.57 29	94.67 25	75.57 22	95.79 59	86.77 45	95.76 23

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

GSMVS																88.96 285

sam_mvs1												51.32 301				88.96 285

sam_mvs												50.01 317

MTGPA								92.02 98

test_post1							78.90 365				5.43 460	48.81 336	85.44 363	59.25 324

test_post											5.46 459	50.36 313	84.24 371

patchmatchnet-post											74.00 427	51.12 304	88.60 325

MTMP							92.18 35	32.83 463

test9_res														84.90 57	95.70 26	92.87 128

agg_prior2														82.91 84	95.45 29	92.70 133

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							86.56 214		58.10 399	87.04 55			88.98 317	74.07 180

新几何2							86.29 224

无先验							87.48 177	88.98 217	60.00 380				94.12 134	67.28 254		88.97 284

原ACMM2							86.86 201

testdata2													91.01 280	62.37 295

segment_acmp												73.08 40

testdata1							84.14 283		75.71 100

plane_prior5								92.44 78					95.38 78	78.71 126	86.32 182	91.33 188

plane_prior4											91.00 145

plane_prior2							91.25 55		79.12 28

plane_prior1					89.90 120

n2								0.00 470

nn								0.00 470

door-mid								69.98 426

test11								92.23 88

door								69.44 429

HQP-NCC					89.33 140		89.17 109		76.41 85	77.23 217

ACMP_Plane					89.33 140		89.17 109		76.41 85	77.23 217

BP-MVS														77.47 140

HQP4-MVS										77.24 216			95.11 90			91.03 198

HQP3-MVS								92.19 92							85.99 190

HQP2-MVS												60.17 215

ACMMP++_ref															81.95 259

ACMMP++															81.25 264

Test By Simon												64.33 146

High-resolution multi-view benchmark