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.

SMA-MVS		89.08 7	89.23 7	88.61 5	94.25 31	73.73 9	92.40 23	93.63 21	74.77 106	92.29 7	95.97 2	74.28 29	97.24 11	88.58 15	96.91 1	94.87 15
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
DVP-MVS++		90.23 1	91.01 1	87.89 23	94.34 27	71.25 56	95.06 1	94.23 3	78.38 32	92.78 4	95.74 6	82.45 3	97.49 3	89.42 5	96.68 2	94.95 9

PC_three_1452									68.21 231	92.02 12	94.00 41	82.09 5	95.98 50	84.58 38	96.68 2	94.95 9

SED-MVS		90.08 2	90.85 2	87.77 25	95.30 2	70.98 62	93.57 7	94.06 10	77.24 49	93.10 1	95.72 8	82.99 1	97.44 5	89.07 10	96.63 4	94.88 13

IU-MVS					95.30 2	71.25 56		92.95 51	66.81 239	92.39 6				88.94 12	96.63 4	94.85 18

test_241102_TWO								94.06 10	77.24 49	92.78 4	95.72 8	81.26 8	97.44 5	89.07 10	96.58 6	94.26 40

test_0728_THIRD									78.38 32	92.12 9	95.78 4	81.46 7	97.40 7	89.42 5	96.57 7	94.67 23

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 40	82.45 3	96.87 19	83.77 48	96.48 8	94.88 13

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 45					97.53 1	89.67 2	96.44 9	94.41 31

No_MVS				89.16 1	94.34 27	75.53 2		92.99 45					97.53 1	89.67 2	96.44 9	94.41 31

HPM-MVS++		89.02 8	89.15 8	88.63 4	95.01 9	76.03 1	92.38 26	92.85 54	80.26 10	87.78 28	94.27 31	75.89 19	96.81 22	87.45 22	96.44 9	93.05 88

DVP-MVS		89.60 3	90.35 3	87.33 39	95.27 5	71.25 56	93.49 9	92.73 59	77.33 47	92.12 9	95.78 4	80.98 9	97.40 7	89.08 8	96.41 12	93.33 78
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				87.71 31	95.34 1	71.43 55	93.49 9	94.23 3					97.49 3	89.08 8	96.41 12	94.21 41

ACMMP_NAP		88.05 16	88.08 16	87.94 18	93.70 41	73.05 21	90.86 55	93.59 23	76.27 78	88.14 24	95.09 15	71.06 53	96.67 28	87.67 19	96.37 14	94.09 45

DPE-MVS		89.48 5	89.98 4	88.01 15	94.80 11	72.69 30	91.59 42	94.10 8	75.90 84	92.29 7	95.66 10	81.67 6	97.38 9	87.44 23	96.34 15	93.95 50
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS-pluss		87.67 20	87.72 20	87.54 35	93.64 44	72.04 47	89.80 78	93.50 25	75.17 99	86.34 34	95.29 12	70.86 54	96.00 48	88.78 13	96.04 16	94.58 26
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SF-MVS		88.46 11	88.74 11	87.64 34	92.78 61	71.95 49	92.40 23	94.74 2	75.71 86	89.16 19	95.10 14	75.65 21	96.19 42	87.07 24	96.01 17	94.79 20

CNVR-MVS		88.93 9	89.13 9	88.33 7	94.77 12	73.82 8	90.51 60	93.00 43	80.90 6	88.06 26	94.06 39	76.43 16	96.84 20	88.48 17	95.99 18	94.34 36

PHI-MVS		86.43 38	86.17 42	87.24 40	90.88 87	70.96 64	92.27 31	94.07 9	72.45 148	85.22 44	91.90 82	69.47 69	96.42 36	83.28 52	95.94 19	94.35 35

test_prior2							88.85 103		75.41 92	84.91 49	93.54 48	74.28 29		83.31 51	95.86 20

SteuartSystems-ACMMP		88.72 10	88.86 10	88.32 8	92.14 69	72.96 24	93.73 5	93.67 20	80.19 11	88.10 25	94.80 16	73.76 33	97.11 14	87.51 21	95.82 21	94.90 12
Skip Steuart: Steuart Systems R&D Blog.
ZNCC-MVS		87.94 18	87.85 19	88.20 11	94.39 24	73.33 18	93.03 14	93.81 17	76.81 62	85.24 43	94.32 30	71.76 46	96.93 18	85.53 29	95.79 22	94.32 37

9.14			88.26 14		92.84 60		91.52 45	94.75 1	73.93 124	88.57 22	94.67 18	75.57 22	95.79 52	86.77 25	95.76 23

DeepPCF-MVS	80.84 1	88.10 12	88.56 12	86.73 49	92.24 68	69.03 96	89.57 84	93.39 30	77.53 44	89.79 18	94.12 36	78.98 12	96.58 34	85.66 27	95.72 24	94.58 26

train_agg		86.43 38	86.20 40	87.13 43	93.26 50	72.96 24	88.75 107	91.89 93	68.69 223	85.00 47	93.10 57	74.43 26	95.41 66	84.97 31	95.71 25	93.02 90

test9_res														84.90 32	95.70 26	92.87 94

APDe-MVS		89.15 6	89.63 6	87.73 27	94.49 18	71.69 51	93.83 4	93.96 13	75.70 88	91.06 16	96.03 1	76.84 14	97.03 16	89.09 7	95.65 27	94.47 30

MVS_0304		88.08 13	88.08 16	88.08 13	89.67 113	72.04 47	92.26 32	89.26 169	84.19 1	85.01 45	95.18 13	69.93 64	97.20 13	91.63 1	95.60 28	94.99 8

agg_prior2														82.91 56	95.45 29	92.70 97

CDPH-MVS		85.76 48	85.29 56	87.17 42	93.49 47	71.08 60	88.58 115	92.42 72	68.32 230	84.61 57	93.48 49	72.32 41	96.15 44	79.00 88	95.43 30	94.28 39

DeepC-MVS	79.81 2	87.08 31	86.88 33	87.69 32	91.16 80	72.32 42	90.31 67	93.94 14	77.12 54	82.82 86	94.23 33	72.13 44	97.09 15	84.83 35	95.37 31	93.65 65
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MTAPA		87.23 27	87.00 28	87.90 21	94.18 35	74.25 5	86.58 177	92.02 85	79.45 18	85.88 36	94.80 16	68.07 80	96.21 41	86.69 26	95.34 32	93.23 81

DeepC-MVS_fast	79.65 3	86.91 32	86.62 35	87.76 26	93.52 46	72.37 40	91.26 47	93.04 38	76.62 69	84.22 64	93.36 53	71.44 50	96.76 24	80.82 75	95.33 33	94.16 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		87.71 19	87.64 21	87.93 20	94.36 26	73.88 6	92.71 22	92.65 64	77.57 40	83.84 72	94.40 29	72.24 42	96.28 39	85.65 28	95.30 34	93.62 68
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MCST-MVS		87.37 26	87.25 25	87.73 27	94.53 17	72.46 37	89.82 76	93.82 16	73.07 143	84.86 52	92.89 64	76.22 17	96.33 37	84.89 34	95.13 35	94.40 33

GST-MVS		87.42 24	87.26 24	87.89 23	94.12 36	72.97 23	92.39 25	93.43 28	76.89 60	84.68 53	93.99 43	70.67 57	96.82 21	84.18 46	95.01 36	93.90 53

APD-MVS		87.44 22	87.52 22	87.19 41	94.24 32	72.39 38	91.86 40	92.83 55	73.01 145	88.58 21	94.52 20	73.36 34	96.49 35	84.26 42	95.01 36	92.70 97
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		88.06 14	88.01 18	88.24 10	94.41 22	73.62 10	91.22 51	92.83 55	81.50 4	85.79 38	93.47 51	73.02 39	97.00 17	84.90 32	94.94 38	94.10 44

ACMMPR		87.44 22	87.23 26	88.08 13	94.64 13	73.59 11	93.04 12	93.20 34	76.78 64	84.66 56	94.52 20	68.81 77	96.65 29	84.53 39	94.90 39	94.00 49

CS-MVS-test		86.29 41	86.48 36	85.71 64	91.02 83	67.21 142	92.36 28	93.78 18	78.97 27	83.51 78	91.20 101	70.65 58	95.15 76	81.96 66	94.89 40	94.77 21

HFP-MVS		87.58 21	87.47 23	87.94 18	94.58 16	73.54 14	93.04 12	93.24 33	76.78 64	84.91 49	94.44 27	70.78 55	96.61 31	84.53 39	94.89 40	93.66 61

ZD-MVS					94.38 25	72.22 43		92.67 61	70.98 174	87.75 29	94.07 38	74.01 32	96.70 26	84.66 37	94.84 42

region2R		87.42 24	87.20 27	88.09 12	94.63 14	73.55 12	93.03 14	93.12 37	76.73 67	84.45 60	94.52 20	69.09 73	96.70 26	84.37 41	94.83 43	94.03 48

原ACMM1				84.35 103	93.01 57	68.79 101		92.44 69	63.96 279	81.09 107	91.57 91	66.06 101	95.45 62	67.19 206	94.82 44	88.81 237

HPM-MVS		87.11 29	86.98 29	87.50 37	93.88 39	72.16 44	92.19 33	93.33 31	76.07 81	83.81 73	93.95 45	69.77 67	96.01 47	85.15 30	94.66 45	94.32 37
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DPM-MVS		84.93 60	84.29 65	86.84 46	90.20 99	73.04 22	87.12 159	93.04 38	69.80 196	82.85 85	91.22 100	73.06 38	96.02 46	76.72 116	94.63 46	91.46 138

TSAR-MVS + MP.		88.02 17	88.11 15	87.72 29	93.68 43	72.13 45	91.41 46	92.35 74	74.62 110	88.90 20	93.85 46	75.75 20	96.00 48	87.80 18	94.63 46	95.04 6
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PGM-MVS		86.68 35	86.27 39	87.90 21	94.22 33	73.38 17	90.22 69	93.04 38	75.53 90	83.86 71	94.42 28	67.87 83	96.64 30	82.70 62	94.57 48	93.66 61

XVS		87.18 28	86.91 32	88.00 16	94.42 20	73.33 18	92.78 18	92.99 45	79.14 20	83.67 75	94.17 34	67.45 86	96.60 32	83.06 53	94.50 49	94.07 46

X-MVStestdata		80.37 135	77.83 172	88.00 16	94.42 20	73.33 18	92.78 18	92.99 45	79.14 20	83.67 75	12.47 381	67.45 86	96.60 32	83.06 53	94.50 49	94.07 46

test12				86.80 48	92.63 64	70.70 71		91.79 99		82.71 88		71.67 47	96.16 43		94.50 49	93.54 72

CP-MVS		87.11 29	86.92 31	87.68 33	94.20 34	73.86 7	93.98 3	92.82 58	76.62 69	83.68 74	94.46 24	67.93 81	95.95 51	84.20 45	94.39 52	93.23 81

CSCG		86.41 40	86.19 41	87.07 44	92.91 58	72.48 36	90.81 56	93.56 24	73.95 122	83.16 81	91.07 106	75.94 18	95.19 74	79.94 84	94.38 53	93.55 71

MSLP-MVS++		85.43 53	85.76 48	84.45 99	91.93 72	70.24 75	90.71 57	92.86 53	77.46 46	84.22 64	92.81 68	67.16 90	92.94 176	80.36 80	94.35 54	90.16 183

mPP-MVS		86.67 36	86.32 38	87.72 29	94.41 22	73.55 12	92.74 20	92.22 80	76.87 61	82.81 87	94.25 32	66.44 95	96.24 40	82.88 57	94.28 55	93.38 75

SD-MVS		88.06 14	88.50 13	86.71 50	92.60 66	72.71 28	91.81 41	93.19 35	77.87 35	90.32 17	94.00 41	74.83 23	93.78 135	87.63 20	94.27 56	93.65 65
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
MSP-MVS		89.51 4	89.91 5	88.30 9	94.28 30	73.46 16	92.90 16	94.11 6	80.27 9	91.35 14	94.16 35	78.35 13	96.77 23	89.59 4	94.22 57	94.67 23
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
DELS-MVS		85.41 54	85.30 55	85.77 63	88.49 161	67.93 124	85.52 209	93.44 27	78.70 28	83.63 77	89.03 154	74.57 24	95.71 55	80.26 82	94.04 58	93.66 61
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
EPNet		83.72 68	82.92 77	86.14 58	84.22 250	69.48 89	91.05 54	85.27 251	81.30 5	76.83 180	91.65 87	66.09 100	95.56 57	76.00 122	93.85 59	93.38 75
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EC-MVSNet		86.01 42	86.38 37	84.91 84	89.31 130	66.27 156	92.32 29	93.63 21	79.37 19	84.17 66	91.88 83	69.04 76	95.43 64	83.93 47	93.77 60	93.01 91

3Dnovator+	77.84 4	85.48 51	84.47 64	88.51 6	91.08 81	73.49 15	93.18 11	93.78 18	80.79 7	76.66 185	93.37 52	60.40 178	96.75 25	77.20 107	93.73 61	95.29 4

CS-MVS		86.69 34	86.95 30	85.90 62	90.76 90	67.57 132	92.83 17	93.30 32	79.67 16	84.57 59	92.27 76	71.47 49	95.02 85	84.24 44	93.46 62	95.13 5

CANet		86.45 37	86.10 44	87.51 36	90.09 101	70.94 66	89.70 82	92.59 66	81.78 3	81.32 102	91.43 96	70.34 59	97.23 12	84.26 42	93.36 63	94.37 34

新几何1				83.42 137	93.13 52	70.71 70		85.48 250	57.43 332	81.80 97	91.98 80	63.28 123	92.27 197	64.60 227	92.99 64	87.27 268

HPM-MVS_fast		85.35 55	84.95 60	86.57 52	93.69 42	70.58 74	92.15 35	91.62 103	73.89 125	82.67 89	94.09 37	62.60 134	95.54 59	80.93 73	92.93 65	93.57 70

SR-MVS		86.73 33	86.67 34	86.91 45	94.11 37	72.11 46	92.37 27	92.56 67	74.50 111	86.84 32	94.65 19	67.31 88	95.77 53	84.80 36	92.85 66	92.84 95

旧先验1					91.96 71	65.79 168		86.37 238			93.08 61	69.31 72			92.74 67	88.74 240

3Dnovator	76.31 5	83.38 76	82.31 85	86.59 51	87.94 180	72.94 27	90.64 58	92.14 84	77.21 51	75.47 210	92.83 66	58.56 185	94.72 98	73.24 149	92.71 68	92.13 120

MVS_111021_HR		85.14 57	84.75 61	86.32 54	91.65 76	72.70 29	85.98 192	90.33 139	76.11 80	82.08 92	91.61 90	71.36 52	94.17 119	81.02 72	92.58 69	92.08 121

APD-MVS_3200maxsize		85.97 44	85.88 46	86.22 56	92.69 63	69.53 88	91.93 37	92.99 45	73.54 134	85.94 35	94.51 23	65.80 105	95.61 56	83.04 55	92.51 70	93.53 73

test2506		77.30 210	76.49 206	79.74 236	90.08 102	52.02 342	87.86 142	63.10 371	74.88 103	80.16 117	92.79 69	38.29 340	92.35 194	68.74 192	92.50 71	94.86 16

ECVR-MVS		79.61 148	79.26 139	80.67 218	90.08 102	54.69 326	87.89 140	77.44 333	74.88 103	80.27 114	92.79 69	48.96 281	92.45 188	68.55 193	92.50 71	94.86 16

test1111		79.43 155	79.18 143	80.15 228	89.99 107	53.31 339	87.33 154	77.05 336	75.04 100	80.23 116	92.77 71	48.97 280	92.33 196	68.87 190	92.40 73	94.81 19

patch_mono-2		83.65 69	84.54 63	80.99 210	90.06 106	65.83 165	84.21 237	88.74 194	71.60 163	85.01 45	92.44 74	74.51 25	83.50 316	82.15 65	92.15 74	93.64 67

dcpmvs_2		85.63 50	86.15 43	84.06 116	91.71 75	64.94 187	86.47 180	91.87 95	73.63 130	86.60 33	93.02 62	76.57 15	91.87 212	83.36 50	92.15 74	95.35 2

MAR-MVS		81.84 97	80.70 108	85.27 70	91.32 79	71.53 53	89.82 76	90.92 121	69.77 197	78.50 141	86.21 235	62.36 140	94.52 105	65.36 220	92.05 76	89.77 207
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
TSAR-MVS + GP.		85.71 49	85.33 53	86.84 46	91.34 78	72.50 35	89.07 96	87.28 224	76.41 71	85.80 37	90.22 124	74.15 31	95.37 71	81.82 67	91.88 77	92.65 101

SR-MVS-dyc-post		85.77 47	85.61 49	86.23 55	93.06 55	70.63 72	91.88 38	92.27 76	73.53 135	85.69 39	94.45 25	65.00 113	95.56 57	82.75 58	91.87 78	92.50 106

RE-MVS-def			85.48 50		93.06 55	70.63 72	91.88 38	92.27 76	73.53 135	85.69 39	94.45 25	63.87 119		82.75 58	91.87 78	92.50 106

IS-MVSNet		83.15 78	82.81 78	84.18 109	89.94 109	63.30 222	91.59 42	88.46 200	79.04 24	79.49 123	92.16 78	65.10 110	94.28 111	67.71 199	91.86 80	94.95 9

Vis-MVSNet (Re-imp)		78.36 182	78.45 156	78.07 263	88.64 157	51.78 346	86.70 174	79.63 319	74.14 120	75.11 226	90.83 113	61.29 160	89.75 255	58.10 282	91.60 81	92.69 99

MG-MVS		83.41 74	83.45 69	83.28 142	92.74 62	62.28 238	88.17 128	89.50 160	75.22 95	81.49 101	92.74 72	66.75 91	95.11 79	72.85 152	91.58 82	92.45 109

CPTT-MVS		83.73 67	83.33 71	84.92 83	93.28 49	70.86 68	92.09 36	90.38 135	68.75 222	79.57 122	92.83 66	60.60 174	93.04 174	80.92 74	91.56 83	90.86 157

test222					91.50 77	68.26 118	84.16 238	83.20 284	54.63 343	79.74 119	91.63 89	58.97 183			91.42 84	86.77 281

ETV-MVS		84.90 62	84.67 62	85.59 66	89.39 124	68.66 111	88.74 109	92.64 65	79.97 14	84.10 67	85.71 244	69.32 71	95.38 68	80.82 75	91.37 85	92.72 96

testdata				79.97 231	90.90 86	64.21 202		84.71 257	59.27 318	85.40 41	92.91 63	62.02 147	89.08 267	68.95 189	91.37 85	86.63 285

API-MVS		81.99 95	81.23 99	84.26 107	90.94 85	70.18 81	91.10 52	89.32 165	71.51 165	78.66 137	88.28 176	65.26 108	95.10 82	64.74 226	91.23 87	87.51 262

casdiffmvs_mvg		85.99 43	86.09 45	85.70 65	87.65 192	67.22 141	88.69 111	93.04 38	79.64 17	85.33 42	92.54 73	73.30 35	94.50 106	83.49 49	91.14 88	95.37 1
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet		83.46 73	82.80 79	85.43 68	90.25 98	68.74 105	90.30 68	90.13 145	76.33 77	80.87 110	92.89 64	61.00 166	94.20 117	72.45 158	90.97 89	93.35 77
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	72.83 10	79.77 146	78.33 161	84.09 113	85.17 234	69.91 83	90.57 59	90.97 120	66.70 242	72.17 259	91.91 81	54.70 214	93.96 123	61.81 250	90.95 90	88.41 247

UA-Net		85.08 59	84.96 59	85.45 67	92.07 70	68.07 122	89.78 79	90.86 125	82.48 2	84.60 58	93.20 56	69.35 70	95.22 73	71.39 164	90.88 91	93.07 87

ACMMP		85.89 46	85.39 51	87.38 38	93.59 45	72.63 32	92.74 20	93.18 36	76.78 64	80.73 111	93.82 47	64.33 115	96.29 38	82.67 63	90.69 92	93.23 81
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
casdiffmvs		85.11 58	85.14 57	85.01 78	87.20 207	65.77 169	87.75 143	92.83 55	77.84 36	84.36 63	92.38 75	72.15 43	93.93 129	81.27 71	90.48 93	95.33 3
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_fmvsm_n_1920		85.29 56	85.34 52	85.13 75	86.12 222	69.93 82	88.65 113	90.78 126	69.97 192	88.27 23	93.98 44	71.39 51	91.54 220	88.49 16	90.45 94	93.91 51

UGNet		80.83 118	79.59 130	84.54 94	88.04 177	68.09 121	89.42 85	88.16 202	76.95 58	76.22 197	89.46 143	49.30 274	93.94 126	68.48 194	90.31 95	91.60 130
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
baseline		84.93 60	84.98 58	84.80 88	87.30 205	65.39 178	87.30 155	92.88 52	77.62 38	84.04 69	92.26 77	71.81 45	93.96 123	81.31 70	90.30 96	95.03 7

MVSFormer		82.85 84	82.05 89	85.24 71	87.35 200	70.21 76	90.50 61	90.38 135	68.55 225	81.32 102	89.47 141	61.68 149	93.46 152	78.98 89	90.26 97	92.05 122

lupinMVS		81.39 109	80.27 118	84.76 89	87.35 200	70.21 76	85.55 205	86.41 236	62.85 288	81.32 102	88.61 166	61.68 149	92.24 199	78.41 96	90.26 97	91.83 126

DP-MVS Recon		83.11 81	82.09 88	86.15 57	94.44 19	70.92 67	88.79 105	92.20 81	70.53 182	79.17 127	91.03 109	64.12 117	96.03 45	68.39 196	90.14 99	91.50 135

EIA-MVS		83.31 77	82.80 79	84.82 86	89.59 115	65.59 171	88.21 126	92.68 60	74.66 108	78.96 129	86.42 231	69.06 74	95.26 72	75.54 128	90.09 100	93.62 68

MVS_111021_LR		82.61 87	82.11 87	84.11 110	88.82 148	71.58 52	85.15 212	86.16 241	74.69 107	80.47 113	91.04 107	62.29 141	90.55 246	80.33 81	90.08 101	90.20 182

jason		81.39 109	80.29 117	84.70 90	86.63 217	69.90 84	85.95 193	86.77 232	63.24 281	81.07 108	89.47 141	61.08 165	92.15 201	78.33 97	90.07 102	92.05 122
jason: jason.
test_fmvsmvis_n_1920		84.02 64	83.87 66	84.49 97	84.12 252	69.37 94	88.15 130	87.96 208	70.01 190	83.95 70	93.23 55	68.80 78	91.51 223	88.61 14	89.96 103	92.57 102

LFMVS		81.82 98	81.23 99	83.57 134	91.89 73	63.43 220	89.84 75	81.85 297	77.04 57	83.21 79	93.10 57	52.26 235	93.43 154	71.98 159	89.95 104	93.85 54

MVS		78.19 187	76.99 194	81.78 187	85.66 227	66.99 144	84.66 222	90.47 133	55.08 342	72.02 261	85.27 255	63.83 120	94.11 121	66.10 214	89.80 105	84.24 317

CANet_DTU		80.61 127	79.87 124	82.83 164	85.60 229	63.17 227	87.36 152	88.65 196	76.37 75	75.88 204	88.44 172	53.51 226	93.07 171	73.30 147	89.74 106	92.25 115

PVSNet_Blended		80.98 114	80.34 115	82.90 162	88.85 145	65.40 176	84.43 232	92.00 87	67.62 235	78.11 153	85.05 263	66.02 102	94.27 112	71.52 161	89.50 107	89.01 227

PAPM_NR		83.02 82	82.41 82	84.82 86	92.47 67	66.37 154	87.93 138	91.80 98	73.82 126	77.32 169	90.66 115	67.90 82	94.90 90	70.37 173	89.48 108	93.19 84

114514_t		80.68 125	79.51 131	84.20 108	94.09 38	67.27 139	89.64 83	91.11 118	58.75 323	74.08 240	90.72 114	58.10 188	95.04 84	69.70 181	89.42 109	90.30 179

LCM-MVSNet-Re		77.05 213	76.94 195	77.36 273	87.20 207	51.60 347	80.06 290	80.46 310	75.20 96	67.69 301	86.72 216	62.48 137	88.98 269	63.44 232	89.25 110	91.51 133

alignmvs		85.48 51	85.32 54	85.96 61	89.51 119	69.47 90	89.74 80	92.47 68	76.17 79	87.73 30	91.46 95	70.32 60	93.78 135	81.51 68	88.95 111	94.63 25

VNet		82.21 90	82.41 82	81.62 190	90.82 88	60.93 252	84.47 228	89.78 153	76.36 76	84.07 68	91.88 83	64.71 114	90.26 248	70.68 170	88.89 112	93.66 61

PS-MVSNAJ		81.69 101	81.02 103	83.70 131	89.51 119	68.21 120	84.28 236	90.09 146	70.79 176	81.26 106	85.62 249	63.15 128	94.29 110	75.62 126	88.87 113	88.59 243

canonicalmvs		85.91 45	85.87 47	86.04 59	89.84 111	69.44 93	90.45 65	93.00 43	76.70 68	88.01 27	91.23 99	73.28 36	93.91 130	81.50 69	88.80 114	94.77 21

QAPM		80.88 116	79.50 132	85.03 77	88.01 179	68.97 99	91.59 42	92.00 87	66.63 246	75.15 225	92.16 78	57.70 192	95.45 62	63.52 230	88.76 115	90.66 164

VDD-MVS		83.01 83	82.36 84	84.96 80	91.02 83	66.40 153	88.91 100	88.11 203	77.57 40	84.39 62	93.29 54	52.19 236	93.91 130	77.05 109	88.70 116	94.57 28

PVSNet_Blended_VisFu		82.62 86	81.83 94	84.96 80	90.80 89	69.76 86	88.74 109	91.70 102	69.39 203	78.96 129	88.46 171	65.47 107	94.87 93	74.42 135	88.57 117	90.24 181

xiu_mvs_v2_base		81.69 101	81.05 102	83.60 132	89.15 137	68.03 123	84.46 230	90.02 147	70.67 179	81.30 105	86.53 229	63.17 127	94.19 118	75.60 127	88.54 118	88.57 244

PAPR		81.66 104	80.89 106	83.99 123	90.27 97	64.00 205	86.76 173	91.77 101	68.84 221	77.13 178	89.50 139	67.63 84	94.88 92	67.55 201	88.52 119	93.09 86

MVS_Test		83.15 78	83.06 74	83.41 139	86.86 211	63.21 224	86.11 190	92.00 87	74.31 115	82.87 84	89.44 146	70.03 62	93.21 159	77.39 106	88.50 120	93.81 57

AdaColmap		80.58 130	79.42 133	84.06 116	93.09 54	68.91 100	89.36 87	88.97 184	69.27 206	75.70 207	89.69 133	57.20 199	95.77 53	63.06 235	88.41 121	87.50 263

VDDNet		81.52 106	80.67 109	84.05 118	90.44 95	64.13 204	89.73 81	85.91 244	71.11 171	83.18 80	93.48 49	50.54 259	93.49 149	73.40 146	88.25 122	94.54 29

PCF-MVS	73.52 7	80.38 133	78.84 149	85.01 78	87.71 189	68.99 98	83.65 245	91.46 111	63.00 285	77.77 161	90.28 121	66.10 99	95.09 83	61.40 253	88.22 123	90.94 155
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Effi-MVS+		83.62 71	83.08 73	85.24 71	88.38 166	67.45 134	88.89 101	89.15 175	75.50 91	82.27 90	88.28 176	69.61 68	94.45 108	77.81 101	87.84 124	93.84 56

gg-mvs-nofinetune		69.95 287	67.96 291	75.94 284	83.07 275	54.51 329	77.23 319	70.29 355	63.11 283	70.32 274	62.33 364	43.62 314	88.69 275	53.88 307	87.76 125	84.62 314

xiu_mvs_v1_base_debu		80.80 121	79.72 127	84.03 120	87.35 200	70.19 78	85.56 202	88.77 190	69.06 215	81.83 94	88.16 180	50.91 253	92.85 178	78.29 98	87.56 126	89.06 222

xiu_mvs_v1_base		80.80 121	79.72 127	84.03 120	87.35 200	70.19 78	85.56 202	88.77 190	69.06 215	81.83 94	88.16 180	50.91 253	92.85 178	78.29 98	87.56 126	89.06 222

xiu_mvs_v1_base_debi		80.80 121	79.72 127	84.03 120	87.35 200	70.19 78	85.56 202	88.77 190	69.06 215	81.83 94	88.16 180	50.91 253	92.85 178	78.29 98	87.56 126	89.06 222

CLD-MVS		82.31 89	81.65 95	84.29 106	88.47 162	67.73 128	85.81 200	92.35 74	75.78 85	78.33 146	86.58 226	64.01 118	94.35 109	76.05 121	87.48 129	90.79 158
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CDS-MVSNet		79.07 166	77.70 179	83.17 149	87.60 194	68.23 119	84.40 234	86.20 240	67.49 237	76.36 194	86.54 228	61.54 152	90.79 242	61.86 249	87.33 130	90.49 171
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
diffmvs		82.10 91	81.88 93	82.76 172	83.00 278	63.78 210	83.68 244	89.76 154	72.94 146	82.02 93	89.85 130	65.96 104	90.79 242	82.38 64	87.30 131	93.71 60
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EPP-MVSNet		83.40 75	83.02 75	84.57 92	90.13 100	64.47 197	92.32 29	90.73 127	74.45 114	79.35 125	91.10 104	69.05 75	95.12 77	72.78 153	87.22 132	94.13 43

TAMVS		78.89 171	77.51 184	83.03 156	87.80 185	67.79 127	84.72 221	85.05 254	67.63 234	76.75 183	87.70 189	62.25 142	90.82 241	58.53 278	87.13 133	90.49 171

TAPA-MVS	73.13 9	79.15 163	77.94 168	82.79 169	89.59 115	62.99 231	88.16 129	91.51 107	65.77 255	77.14 177	91.09 105	60.91 167	93.21 159	50.26 327	87.05 134	92.17 119
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PAPM		77.68 203	76.40 209	81.51 193	87.29 206	61.85 243	83.78 243	89.59 158	64.74 266	71.23 267	88.70 162	62.59 135	93.66 142	52.66 313	87.03 135	89.01 227

test_yl		81.17 111	80.47 113	83.24 145	89.13 138	63.62 211	86.21 187	89.95 150	72.43 151	81.78 98	89.61 136	57.50 195	93.58 143	70.75 168	86.90 136	92.52 104

DCV-MVSNet		81.17 111	80.47 113	83.24 145	89.13 138	63.62 211	86.21 187	89.95 150	72.43 151	81.78 98	89.61 136	57.50 195	93.58 143	70.75 168	86.90 136	92.52 104

BH-untuned		79.47 153	78.60 153	82.05 182	89.19 136	65.91 163	86.07 191	88.52 199	72.18 153	75.42 214	87.69 190	61.15 163	93.54 147	60.38 260	86.83 138	86.70 283

BH-RMVSNet		79.61 148	78.44 157	83.14 150	89.38 125	65.93 162	84.95 217	87.15 227	73.56 133	78.19 151	89.79 131	56.67 202	93.36 155	59.53 267	86.74 139	90.13 185

LS3D		76.95 216	74.82 229	83.37 140	90.45 94	67.36 138	89.15 94	86.94 230	61.87 299	69.52 287	90.61 116	51.71 247	94.53 104	46.38 347	86.71 140	88.21 249

Fast-Effi-MVS+		80.81 119	79.92 122	83.47 135	88.85 145	64.51 194	85.53 207	89.39 163	70.79 176	78.49 142	85.06 262	67.54 85	93.58 143	67.03 209	86.58 141	92.32 112

EPNet_dtu		75.46 237	74.86 228	77.23 276	82.57 288	54.60 327	86.89 166	83.09 285	71.64 158	66.25 319	85.86 242	55.99 204	88.04 283	54.92 302	86.55 142	89.05 225
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OPM-MVS		83.50 72	82.95 76	85.14 73	88.79 151	70.95 65	89.13 95	91.52 106	77.55 43	80.96 109	91.75 85	60.71 169	94.50 106	79.67 85	86.51 143	89.97 199
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
OMC-MVS		82.69 85	81.97 92	84.85 85	88.75 153	67.42 135	87.98 134	90.87 124	74.92 102	79.72 120	91.65 87	62.19 144	93.96 123	75.26 130	86.42 144	93.16 85

HQP_MVS		83.64 70	83.14 72	85.14 73	90.08 102	68.71 107	91.25 49	92.44 69	79.12 22	78.92 131	91.00 110	60.42 176	95.38 68	78.71 92	86.32 145	91.33 139

plane_prior5								92.44 69					95.38 68	78.71 92	86.32 145	91.33 139

FA-MVS(test-final)		80.96 115	79.91 123	84.10 111	88.30 169	65.01 185	84.55 227	90.01 148	73.25 140	79.61 121	87.57 193	58.35 187	94.72 98	71.29 165	86.25 147	92.56 103

thisisatest0515		77.33 209	75.38 223	83.18 148	85.27 233	63.80 209	82.11 266	83.27 281	65.06 262	75.91 203	83.84 279	49.54 269	94.27 112	67.24 205	86.19 148	91.48 137

plane_prior						68.71 107	90.38 66		77.62 38						86.16 149

mvs_anonymous		79.42 156	79.11 144	80.34 224	84.45 247	57.97 284	82.59 262	87.62 217	67.40 238	76.17 201	88.56 169	68.47 79	89.59 258	70.65 171	86.05 150	93.47 74

GeoE		81.71 100	81.01 104	83.80 129	89.51 119	64.45 198	88.97 98	88.73 195	71.27 168	78.63 138	89.76 132	66.32 97	93.20 162	69.89 179	86.02 151	93.74 59

HQP3-MVS								92.19 82							85.99 152

HQP-MVS		82.61 87	82.02 90	84.37 101	89.33 127	66.98 145	89.17 90	92.19 82	76.41 71	77.23 172	90.23 123	60.17 179	95.11 79	77.47 104	85.99 152	91.03 151

BH-w/o		78.21 185	77.33 188	80.84 214	88.81 149	65.13 183	84.87 218	87.85 213	69.75 198	74.52 236	84.74 267	61.34 158	93.11 169	58.24 281	85.84 154	84.27 316

FE-MVS		77.78 198	75.68 216	84.08 114	88.09 175	66.00 160	83.13 256	87.79 214	68.42 229	78.01 156	85.23 257	45.50 305	95.12 77	59.11 271	85.83 155	91.11 146

CHOSEN 1792x2688		77.63 204	75.69 215	83.44 136	89.98 108	68.58 113	78.70 307	87.50 220	56.38 337	75.80 206	86.84 212	58.67 184	91.40 226	61.58 252	85.75 156	90.34 176

Anonymous202405211		78.25 183	77.01 192	81.99 184	91.03 82	60.67 257	84.77 220	83.90 271	70.65 181	80.00 118	91.20 101	41.08 330	91.43 225	65.21 221	85.26 157	93.85 54

cascas		76.72 219	74.64 230	82.99 158	85.78 226	65.88 164	82.33 264	89.21 172	60.85 305	72.74 251	81.02 311	47.28 288	93.75 139	67.48 202	85.02 158	89.34 216

FIs		82.07 93	82.42 81	81.04 209	88.80 150	58.34 278	88.26 125	93.49 26	76.93 59	78.47 143	91.04 107	69.92 65	92.34 195	69.87 180	84.97 159	92.44 110

test-LLR		72.94 263	72.43 253	74.48 299	81.35 307	58.04 282	78.38 308	77.46 331	66.66 243	69.95 282	79.00 329	48.06 284	79.24 333	66.13 212	84.83 160	86.15 291

test-mter		71.41 271	70.39 274	74.48 299	81.35 307	58.04 282	78.38 308	77.46 331	60.32 308	69.95 282	79.00 329	36.08 347	79.24 333	66.13 212	84.83 160	86.15 291

EI-MVSNet-Vis-set		84.19 63	83.81 67	85.31 69	88.18 171	67.85 125	87.66 145	89.73 156	80.05 13	82.95 82	89.59 138	70.74 56	94.82 94	80.66 79	84.72 162	93.28 80

thisisatest0530		79.40 157	77.76 177	84.31 105	87.69 191	65.10 184	87.36 152	84.26 267	70.04 189	77.42 166	88.26 178	49.94 265	94.79 96	70.20 174	84.70 163	93.03 89

GG-mvs-BLEND				75.38 291	81.59 302	55.80 316	79.32 298	69.63 357		67.19 307	73.67 354	43.24 315	88.90 273	50.41 322	84.50 164	81.45 341

FC-MVSNet-test		81.52 106	82.02 90	80.03 230	88.42 165	55.97 315	87.95 136	93.42 29	77.10 55	77.38 167	90.98 112	69.96 63	91.79 213	68.46 195	84.50 164	92.33 111

iter_conf_final		80.63 126	79.35 136	84.46 98	89.36 126	67.70 129	89.85 74	84.49 261	73.19 141	78.30 147	88.94 155	45.98 298	94.56 101	79.59 86	84.48 166	91.11 146

PVSNet	64.34 18	72.08 269	70.87 268	75.69 286	86.21 221	56.44 308	74.37 336	80.73 305	62.06 298	70.17 277	82.23 302	42.86 318	83.31 318	54.77 303	84.45 167	87.32 267

MS-PatchMatch		73.83 251	72.67 251	77.30 275	83.87 258	66.02 159	81.82 267	84.66 258	61.37 303	68.61 295	82.82 294	47.29 287	88.21 280	59.27 268	84.32 168	77.68 353

iter_conf05		80.00 144	78.70 150	83.91 127	87.84 183	65.83 165	88.84 104	84.92 256	71.61 162	78.70 134	88.94 155	43.88 313	94.56 101	79.28 87	84.28 169	91.33 139

ET-MVSNet_ETH3D		78.63 176	76.63 205	84.64 91	86.73 216	69.47 90	85.01 215	84.61 259	69.54 201	66.51 317	86.59 224	50.16 262	91.75 214	76.26 118	84.24 170	92.69 99

TESTMET0.1,1		69.89 288	69.00 282	72.55 314	79.27 334	56.85 300	78.38 308	74.71 347	57.64 330	68.09 298	77.19 342	37.75 342	76.70 346	63.92 229	84.09 171	84.10 320

EI-MVSNet-UG-set		83.81 66	83.38 70	85.09 76	87.87 181	67.53 133	87.44 151	89.66 157	79.74 15	82.23 91	89.41 147	70.24 61	94.74 97	79.95 83	83.92 172	92.99 92

LPG-MVS_test		82.08 92	81.27 98	84.50 95	89.23 134	68.76 103	90.22 69	91.94 91	75.37 93	76.64 186	91.51 92	54.29 218	94.91 87	78.44 94	83.78 173	89.83 204

LGP-MVS_train				84.50 95	89.23 134	68.76 103		91.94 91	75.37 93	76.64 186	91.51 92	54.29 218	94.91 87	78.44 94	83.78 173	89.83 204

thres100view900		76.50 221	75.55 219	79.33 244	89.52 118	56.99 299	85.83 199	83.23 282	73.94 123	76.32 195	87.12 208	51.89 244	91.95 207	48.33 335	83.75 175	89.07 220

tfpn200view9		76.42 224	75.37 224	79.55 243	89.13 138	57.65 290	85.17 210	83.60 274	73.41 137	76.45 190	86.39 232	52.12 237	91.95 207	48.33 335	83.75 175	89.07 220

thres400		76.50 221	75.37 224	79.86 233	89.13 138	57.65 290	85.17 210	83.60 274	73.41 137	76.45 190	86.39 232	52.12 237	91.95 207	48.33 335	83.75 175	90.00 195

thres600view7		76.50 221	75.44 220	79.68 238	89.40 123	57.16 296	85.53 207	83.23 282	73.79 128	76.26 196	87.09 209	51.89 244	91.89 210	48.05 340	83.72 178	90.00 195

thres200		75.55 235	74.47 234	78.82 250	87.78 188	57.85 287	83.07 259	83.51 277	72.44 150	75.84 205	84.42 269	52.08 239	91.75 214	47.41 342	83.64 179	86.86 279

SDMVSNet		80.38 133	80.18 119	80.99 210	89.03 143	64.94 187	80.45 286	89.40 162	75.19 97	76.61 188	89.98 127	60.61 173	87.69 287	76.83 113	83.55 180	90.33 177

sd_testset		77.70 202	77.40 185	78.60 254	89.03 143	60.02 266	79.00 303	85.83 246	75.19 97	76.61 188	89.98 127	54.81 209	85.46 302	62.63 241	83.55 180	90.33 177

mvsmamba		81.69 101	80.74 107	84.56 93	87.45 199	66.72 149	91.26 47	85.89 245	74.66 108	78.23 149	90.56 117	54.33 217	94.91 87	80.73 78	83.54 182	92.04 124

XVG-OURS		80.41 132	79.23 140	83.97 124	85.64 228	69.02 97	83.03 260	90.39 134	71.09 172	77.63 163	91.49 94	54.62 216	91.35 227	75.71 124	83.47 183	91.54 132

CNLPA		78.08 189	76.79 199	81.97 185	90.40 96	71.07 61	87.59 147	84.55 260	66.03 253	72.38 257	89.64 135	57.56 194	86.04 297	59.61 266	83.35 184	88.79 238

MVP-Stereo		76.12 228	74.46 235	81.13 207	85.37 232	69.79 85	84.42 233	87.95 209	65.03 263	67.46 304	85.33 254	53.28 228	91.73 216	58.01 283	83.27 185	81.85 339
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
1314		76.53 220	75.30 226	80.21 227	83.93 257	62.32 237	84.66 222	88.81 188	60.23 309	70.16 278	84.07 276	55.30 207	90.73 244	67.37 203	83.21 186	87.59 261

tttt0517		79.40 157	77.91 169	83.90 128	88.10 174	63.84 208	88.37 122	84.05 269	71.45 166	76.78 182	89.12 151	49.93 267	94.89 91	70.18 175	83.18 187	92.96 93

HyFIR lowres test		77.53 205	75.40 222	83.94 126	89.59 115	66.62 150	80.36 287	88.64 197	56.29 338	76.45 190	85.17 259	57.64 193	93.28 157	61.34 255	83.10 188	91.91 125

ACMP	74.13 6	81.51 108	80.57 110	84.36 102	89.42 122	68.69 110	89.97 73	91.50 110	74.46 113	75.04 229	90.41 120	53.82 223	94.54 103	77.56 103	82.91 189	89.86 203
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	73.20 8	80.78 124	79.84 125	83.58 133	89.31 130	68.37 115	89.99 72	91.60 104	70.28 186	77.25 170	89.66 134	53.37 227	93.53 148	74.24 138	82.85 190	88.85 235
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PMMVS		69.34 291	68.67 283	71.35 323	75.67 347	62.03 240	75.17 330	73.46 350	50.00 354	68.68 293	79.05 327	52.07 240	78.13 338	61.16 256	82.77 191	73.90 359

PLC	70.83 11	78.05 191	76.37 210	83.08 153	91.88 74	67.80 126	88.19 127	89.46 161	64.33 272	69.87 284	88.38 173	53.66 224	93.58 143	58.86 274	82.73 192	87.86 254
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TR-MVS		77.44 206	76.18 211	81.20 204	88.24 170	63.24 223	84.61 225	86.40 237	67.55 236	77.81 159	86.48 230	54.10 220	93.15 166	57.75 285	82.72 193	87.20 269

Anonymous20240529		80.19 140	78.89 148	84.10 111	90.60 91	64.75 191	88.95 99	90.90 122	65.97 254	80.59 112	91.17 103	49.97 264	93.73 141	69.16 187	82.70 194	93.81 57

ab-mvs		79.51 151	78.97 147	81.14 206	88.46 163	60.91 253	83.84 242	89.24 171	70.36 184	79.03 128	88.87 159	63.23 126	90.21 250	65.12 222	82.57 195	92.28 114

HY-MVS	69.67 12	77.95 194	77.15 190	80.36 223	87.57 198	60.21 265	83.37 252	87.78 215	66.11 250	75.37 216	87.06 211	63.27 124	90.48 247	61.38 254	82.43 196	90.40 175

PS-MVSNAJss		82.07 93	81.31 97	84.34 104	86.51 218	67.27 139	89.27 88	91.51 107	71.75 157	79.37 124	90.22 124	63.15 128	94.27 112	77.69 102	82.36 197	91.49 136

UniMVSNet_ETH3D		79.10 165	78.24 163	81.70 189	86.85 212	60.24 264	87.28 156	88.79 189	74.25 117	76.84 179	90.53 119	49.48 270	91.56 219	67.98 197	82.15 198	93.29 79

PVSNet_BlendedMVS		80.60 128	80.02 120	82.36 179	88.85 145	65.40 176	86.16 189	92.00 87	69.34 205	78.11 153	86.09 239	66.02 102	94.27 112	71.52 161	82.06 199	87.39 264

WTY-MVS		75.65 234	75.68 216	75.57 288	86.40 219	56.82 301	77.92 315	82.40 291	65.10 261	76.18 199	87.72 188	63.13 131	80.90 328	60.31 261	81.96 200	89.00 229

ACMMP++_ref															81.95 201

DP-MVS		76.78 218	74.57 231	83.42 137	93.29 48	69.46 92	88.55 116	83.70 273	63.98 278	70.20 275	88.89 158	54.01 222	94.80 95	46.66 344	81.88 202	86.01 295

CMPMVS	51.72 21	70.19 285	68.16 288	76.28 282	73.15 360	57.55 292	79.47 297	83.92 270	48.02 356	56.48 359	84.81 265	43.13 316	86.42 295	62.67 240	81.81 203	84.89 310
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
bld_raw_dy_0_64		77.29 211	75.98 213	81.22 203	85.04 240	65.47 174	88.14 132	77.56 330	69.20 210	73.77 242	89.40 149	42.24 324	88.85 274	76.78 114	81.64 204	89.33 217

XVG-OURS-SEG-HR		80.81 119	79.76 126	83.96 125	85.60 229	68.78 102	83.54 250	90.50 132	70.66 180	76.71 184	91.66 86	60.69 170	91.26 229	76.94 110	81.58 205	91.83 126

MIMVSNet		70.69 279	69.30 278	74.88 295	84.52 245	56.35 311	75.87 326	79.42 320	64.59 267	67.76 299	82.41 298	41.10 329	81.54 325	46.64 346	81.34 206	86.75 282

ACMMP++															81.25 207

D2MVS		74.82 242	73.21 247	79.64 240	79.81 325	62.56 234	80.34 288	87.35 223	64.37 271	68.86 292	82.66 296	46.37 294	90.10 251	67.91 198	81.24 208	86.25 288

test_vis1_n_1920		75.52 236	75.78 214	74.75 298	79.84 324	57.44 294	83.26 253	85.52 249	62.83 289	79.34 126	86.17 237	45.10 307	79.71 332	78.75 91	81.21 209	87.10 276

GA-MVS		76.87 217	75.17 227	81.97 185	82.75 283	62.58 233	81.44 275	86.35 239	72.16 155	74.74 233	82.89 292	46.20 297	92.02 205	68.85 191	81.09 210	91.30 142

sss		73.60 253	73.64 244	73.51 307	82.80 282	55.01 324	76.12 322	81.69 298	62.47 294	74.68 234	85.85 243	57.32 197	78.11 339	60.86 258	80.93 211	87.39 264

Effi-MVS+-dtu		80.03 142	78.57 154	84.42 100	85.13 238	68.74 105	88.77 106	88.10 204	74.99 101	74.97 230	83.49 285	57.27 198	93.36 155	73.53 143	80.88 212	91.18 144

EG-PatchMatch MVS		74.04 249	71.82 258	80.71 217	84.92 241	67.42 135	85.86 197	88.08 205	66.04 252	64.22 331	83.85 278	35.10 349	92.56 185	57.44 287	80.83 213	82.16 338

jajsoiax		79.29 160	77.96 167	83.27 143	84.68 244	66.57 152	89.25 89	90.16 144	69.20 210	75.46 212	89.49 140	45.75 303	93.13 168	76.84 111	80.80 214	90.11 187

1112_ss		77.40 208	76.43 208	80.32 225	89.11 142	60.41 262	83.65 245	87.72 216	62.13 297	73.05 249	86.72 216	62.58 136	89.97 252	62.11 247	80.80 214	90.59 168

mvs_tets		79.13 164	77.77 176	83.22 147	84.70 243	66.37 154	89.17 90	90.19 143	69.38 204	75.40 215	89.46 143	44.17 311	93.15 166	76.78 114	80.70 216	90.14 184

PatchMatch-RL		72.38 266	70.90 267	76.80 280	88.60 158	67.38 137	79.53 296	76.17 341	62.75 291	69.36 289	82.00 306	45.51 304	84.89 307	53.62 308	80.58 217	78.12 352

EI-MVSNet		80.52 131	79.98 121	82.12 180	84.28 248	63.19 226	86.41 181	88.95 185	74.18 119	78.69 135	87.54 196	66.62 92	92.43 189	72.57 156	80.57 218	90.74 162

MVSTER		79.01 167	77.88 171	82.38 178	83.07 275	64.80 190	84.08 241	88.95 185	69.01 218	78.69 135	87.17 207	54.70 214	92.43 189	74.69 132	80.57 218	89.89 202

XVG-ACMP-BASELINE		76.11 229	74.27 237	81.62 190	83.20 271	64.67 192	83.60 248	89.75 155	69.75 198	71.85 262	87.09 209	32.78 352	92.11 202	69.99 178	80.43 220	88.09 250

Fast-Effi-MVS+-dtu		78.02 192	76.49 206	82.62 174	83.16 274	66.96 147	86.94 164	87.45 222	72.45 148	71.49 266	84.17 274	54.79 213	91.58 218	67.61 200	80.31 221	89.30 218

LTVRE_ROB	69.57 13	76.25 227	74.54 233	81.41 196	88.60 158	64.38 200	79.24 299	89.12 178	70.76 178	69.79 286	87.86 187	49.09 277	93.20 162	56.21 299	80.16 222	86.65 284
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
Test_1112_low_res		76.40 225	75.44 220	79.27 245	89.28 132	58.09 280	81.69 270	87.07 228	59.53 316	72.48 255	86.67 221	61.30 159	89.33 262	60.81 259	80.15 223	90.41 174

test_djsdf		80.30 137	79.32 137	83.27 143	83.98 256	65.37 179	90.50 61	90.38 135	68.55 225	76.19 198	88.70 162	56.44 203	93.46 152	78.98 89	80.14 224	90.97 154

test_fmvs1		70.93 276	70.52 270	72.16 316	73.71 355	55.05 323	80.82 277	78.77 324	51.21 353	78.58 139	84.41 270	31.20 356	76.94 345	75.88 123	80.12 225	84.47 315

test_fmvs1_n		70.86 277	70.24 275	72.73 313	72.51 363	55.28 321	81.27 276	79.71 318	51.49 352	78.73 133	84.87 264	27.54 360	77.02 344	76.06 120	79.97 226	85.88 298

CHOSEN 280x420		66.51 309	64.71 310	71.90 317	81.45 304	63.52 216	57.98 371	68.95 361	53.57 344	62.59 340	76.70 343	46.22 296	75.29 358	55.25 301	79.68 227	76.88 355

baseline2		75.70 233	73.83 242	81.30 200	83.26 269	61.79 245	82.57 263	80.65 306	66.81 239	66.88 310	83.42 286	57.86 191	92.19 200	63.47 231	79.57 228	89.91 200

GBi-Net		78.40 180	77.40 185	81.40 197	87.60 194	63.01 228	88.39 119	89.28 166	71.63 159	75.34 217	87.28 200	54.80 210	91.11 232	62.72 237	79.57 228	90.09 189

test1		78.40 180	77.40 185	81.40 197	87.60 194	63.01 228	88.39 119	89.28 166	71.63 159	75.34 217	87.28 200	54.80 210	91.11 232	62.72 237	79.57 228	90.09 189

FMVSNet3		77.88 196	76.85 197	80.97 212	86.84 213	62.36 235	86.52 179	88.77 190	71.13 170	75.34 217	86.66 222	54.07 221	91.10 235	62.72 237	79.57 228	89.45 214

FMVSNet2		78.20 186	77.21 189	81.20 204	87.60 194	62.89 232	87.47 150	89.02 180	71.63 159	75.29 222	87.28 200	54.80 210	91.10 235	62.38 242	79.38 232	89.61 211

anonymousdsp		78.60 177	77.15 190	82.98 159	80.51 317	67.08 143	87.24 157	89.53 159	65.66 257	75.16 224	87.19 206	52.52 230	92.25 198	77.17 108	79.34 233	89.61 211

nrg030		83.88 65	83.53 68	84.96 80	86.77 215	69.28 95	90.46 64	92.67 61	74.79 105	82.95 82	91.33 98	72.70 40	93.09 170	80.79 77	79.28 234	92.50 106

VPA-MVSNet		80.60 128	80.55 111	80.76 216	88.07 176	60.80 255	86.86 167	91.58 105	75.67 89	80.24 115	89.45 145	63.34 122	90.25 249	70.51 172	79.22 235	91.23 143

RRT_MVS		80.35 136	79.22 141	83.74 130	87.63 193	65.46 175	91.08 53	88.92 187	73.82 126	76.44 193	90.03 126	49.05 279	94.25 116	76.84 111	79.20 236	91.51 133

tt0805		78.73 173	77.83 172	81.43 195	85.17 234	60.30 263	89.41 86	90.90 122	71.21 169	77.17 176	88.73 161	46.38 293	93.21 159	72.57 156	78.96 237	90.79 158

test_cas_vis1_n_1920		73.76 252	73.74 243	73.81 305	75.90 345	59.77 268	80.51 284	82.40 291	58.30 325	81.62 100	85.69 245	44.35 310	76.41 350	76.29 117	78.61 238	85.23 305

F-COLMAP		76.38 226	74.33 236	82.50 176	89.28 132	66.95 148	88.41 118	89.03 179	64.05 276	66.83 311	88.61 166	46.78 291	92.89 177	57.48 286	78.55 239	87.67 257

FMVSNet1		77.44 206	76.12 212	81.40 197	86.81 214	63.01 228	88.39 119	89.28 166	70.49 183	74.39 237	87.28 200	49.06 278	91.11 232	60.91 257	78.52 240	90.09 189

MDTV_nov1_ep13			69.97 277		83.18 272	53.48 336	77.10 320	80.18 315	60.45 306	69.33 290	80.44 317	48.89 282	86.90 291	51.60 318	78.51 241

CVMVSNet		72.99 262	72.58 252	74.25 302	84.28 248	50.85 352	86.41 181	83.45 279	44.56 359	73.23 247	87.54 196	49.38 272	85.70 299	65.90 216	78.44 242	86.19 290

tpm2		73.26 258	71.46 260	78.63 252	83.34 267	56.71 304	80.65 282	80.40 311	56.63 336	73.55 243	82.02 305	51.80 246	91.24 230	56.35 298	78.42 243	87.95 251

test_vis1_n		69.85 289	69.21 280	71.77 318	72.66 362	55.27 322	81.48 273	76.21 340	52.03 349	75.30 221	83.20 289	28.97 358	76.22 352	74.60 133	78.41 244	83.81 323

CostFormer		75.24 241	73.90 240	79.27 245	82.65 287	58.27 279	80.80 278	82.73 289	61.57 300	75.33 220	83.13 290	55.52 205	91.07 238	64.98 224	78.34 245	88.45 245

ACMH	67.68 16	75.89 231	73.93 239	81.77 188	88.71 155	66.61 151	88.62 114	89.01 181	69.81 195	66.78 312	86.70 220	41.95 327	91.51 223	55.64 300	78.14 246	87.17 270
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
dmvs_re		71.14 273	70.58 269	72.80 312	81.96 296	59.68 269	75.60 328	79.34 321	68.55 225	69.27 291	80.72 316	49.42 271	76.54 347	52.56 314	77.79 247	82.19 337

CR-MVSNet		73.37 255	71.27 264	79.67 239	81.32 309	65.19 181	75.92 324	80.30 312	59.92 312	72.73 252	81.19 308	52.50 231	86.69 292	59.84 264	77.71 248	87.11 274

RPMNet		73.51 254	70.49 271	82.58 175	81.32 309	65.19 181	75.92 324	92.27 76	57.60 331	72.73 252	76.45 345	52.30 234	95.43 64	48.14 339	77.71 248	87.11 274

SCA		74.22 247	72.33 255	79.91 232	84.05 255	62.17 239	79.96 293	79.29 322	66.30 249	72.38 257	80.13 320	51.95 242	88.60 276	59.25 269	77.67 250	88.96 231

Anonymous20231211		78.97 169	77.69 180	82.81 166	90.54 93	64.29 201	90.11 71	91.51 107	65.01 264	76.16 202	88.13 185	50.56 258	93.03 175	69.68 182	77.56 251	91.11 146

v1144		80.03 142	79.03 145	83.01 157	83.78 259	64.51 194	87.11 160	90.57 131	71.96 156	78.08 155	86.20 236	61.41 156	93.94 126	74.93 131	77.23 252	90.60 167

WR-MVS		79.49 152	79.22 141	80.27 226	88.79 151	58.35 277	85.06 214	88.61 198	78.56 29	77.65 162	88.34 174	63.81 121	90.66 245	64.98 224	77.22 253	91.80 128

v1192		79.59 150	78.43 158	83.07 154	83.55 263	64.52 193	86.93 165	90.58 130	70.83 175	77.78 160	85.90 240	59.15 182	93.94 126	73.96 140	77.19 254	90.76 160

VPNet		78.69 175	78.66 152	78.76 251	88.31 168	55.72 317	84.45 231	86.63 234	76.79 63	78.26 148	90.55 118	59.30 181	89.70 257	66.63 210	77.05 255	90.88 156

v1240		78.99 168	77.78 175	82.64 173	83.21 270	63.54 215	86.62 176	90.30 141	69.74 200	77.33 168	85.68 246	57.04 200	93.76 138	73.13 150	76.92 256	90.62 165

MSDG		73.36 257	70.99 266	80.49 221	84.51 246	65.80 167	80.71 281	86.13 242	65.70 256	65.46 322	83.74 282	44.60 308	90.91 240	51.13 320	76.89 257	84.74 312

IterMVS-LS		80.06 141	79.38 134	82.11 181	85.89 224	63.20 225	86.79 170	89.34 164	74.19 118	75.45 213	86.72 216	66.62 92	92.39 191	72.58 155	76.86 258	90.75 161
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		79.22 161	78.03 166	82.80 167	83.30 268	63.94 207	86.80 169	90.33 139	69.91 194	77.48 165	85.53 250	58.44 186	93.75 139	73.60 142	76.85 259	90.71 163

XXY-MVS		75.41 239	75.56 218	74.96 294	83.59 262	57.82 288	80.59 283	83.87 272	66.54 247	74.93 231	88.31 175	63.24 125	80.09 331	62.16 245	76.85 259	86.97 277

v2v482		80.23 138	79.29 138	83.05 155	83.62 261	64.14 203	87.04 161	89.97 149	73.61 131	78.18 152	87.22 204	61.10 164	93.82 133	76.11 119	76.78 261	91.18 144

v144192		79.47 153	78.37 159	82.78 170	83.35 266	63.96 206	86.96 163	90.36 138	69.99 191	77.50 164	85.67 247	60.66 171	93.77 137	74.27 137	76.58 262	90.62 165

UniMVSNet (Re)		81.60 105	81.11 101	83.09 152	88.38 166	64.41 199	87.60 146	93.02 42	78.42 31	78.56 140	88.16 180	69.78 66	93.26 158	69.58 183	76.49 263	91.60 130

UniMVSNet_NR-MVSNet		81.88 96	81.54 96	82.92 161	88.46 163	63.46 218	87.13 158	92.37 73	80.19 11	78.38 144	89.14 150	71.66 48	93.05 172	70.05 176	76.46 264	92.25 115

DU-MVS		81.12 113	80.52 112	82.90 162	87.80 185	63.46 218	87.02 162	91.87 95	79.01 25	78.38 144	89.07 152	65.02 111	93.05 172	70.05 176	76.46 264	92.20 117

cl22		78.07 190	77.01 192	81.23 202	82.37 293	61.83 244	83.55 249	87.98 207	68.96 219	75.06 228	83.87 277	61.40 157	91.88 211	73.53 143	76.39 266	89.98 198

miper_ehance_all_eth		78.59 178	77.76 177	81.08 208	82.66 286	61.56 247	83.65 245	89.15 175	68.87 220	75.55 209	83.79 281	66.49 94	92.03 204	73.25 148	76.39 266	89.64 210

miper_enhance_ethall		77.87 197	76.86 196	80.92 213	81.65 300	61.38 249	82.68 261	88.98 182	65.52 259	75.47 210	82.30 300	65.76 106	92.00 206	72.95 151	76.39 266	89.39 215

PatchmatchNet		73.12 260	71.33 263	78.49 258	83.18 272	60.85 254	79.63 295	78.57 325	64.13 273	71.73 263	79.81 325	51.20 251	85.97 298	57.40 288	76.36 269	88.66 241
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
USDC		70.33 283	68.37 285	76.21 283	80.60 315	56.23 312	79.19 301	86.49 235	60.89 304	61.29 342	85.47 252	31.78 355	89.47 261	53.37 310	76.21 270	82.94 334

OpenMVS_ROB	64.09 19	70.56 281	68.19 287	77.65 269	80.26 318	59.41 273	85.01 215	82.96 287	58.76 322	65.43 323	82.33 299	37.63 343	91.23 231	45.34 352	76.03 271	82.32 335

ACMH+	68.96 14	76.01 230	74.01 238	82.03 183	88.60 158	65.31 180	88.86 102	87.55 218	70.25 187	67.75 300	87.47 198	41.27 328	93.19 164	58.37 279	75.94 272	87.60 259

tpm		72.37 267	71.71 259	74.35 301	82.19 294	52.00 343	79.22 300	77.29 334	64.56 268	72.95 250	83.68 284	51.35 249	83.26 319	58.33 280	75.80 273	87.81 255

Anonymous20231206		68.60 296	67.80 295	71.02 325	80.23 319	50.75 353	78.30 311	80.47 309	56.79 335	66.11 320	82.63 297	46.35 295	78.95 335	43.62 355	75.70 274	83.36 327

v7n		78.97 169	77.58 183	83.14 150	83.45 265	65.51 172	88.32 123	91.21 114	73.69 129	72.41 256	86.32 234	57.93 189	93.81 134	69.18 186	75.65 275	90.11 187

NR-MVSNet		80.23 138	79.38 134	82.78 170	87.80 185	63.34 221	86.31 184	91.09 119	79.01 25	72.17 259	89.07 152	67.20 89	92.81 181	66.08 215	75.65 275	92.20 117

v10		79.74 147	78.67 151	82.97 160	84.06 254	64.95 186	87.88 141	90.62 129	73.11 142	75.11 226	86.56 227	61.46 155	94.05 122	73.68 141	75.55 277	89.90 201

IB-MVS	68.01 15	75.85 232	73.36 246	83.31 141	84.76 242	66.03 158	83.38 251	85.06 253	70.21 188	69.40 288	81.05 310	45.76 302	94.66 100	65.10 223	75.49 278	89.25 219
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
h-mvs33		83.15 78	82.19 86	86.02 60	90.56 92	70.85 69	88.15 130	89.16 174	76.02 82	84.67 54	91.39 97	61.54 152	95.50 60	82.71 60	75.48 279	91.72 129

c3_l		78.75 172	77.91 169	81.26 201	82.89 281	61.56 247	84.09 240	89.13 177	69.97 192	75.56 208	84.29 273	66.36 96	92.09 203	73.47 145	75.48 279	90.12 186

V42		79.38 159	78.24 163	82.83 164	81.10 311	65.50 173	85.55 205	89.82 152	71.57 164	78.21 150	86.12 238	60.66 171	93.18 165	75.64 125	75.46 281	89.81 206

cl____		77.72 200	76.76 200	80.58 219	82.49 290	60.48 260	83.09 257	87.87 211	69.22 208	74.38 238	85.22 258	62.10 145	91.53 221	71.09 166	75.41 282	89.73 209

DIV-MVS_self_test		77.72 200	76.76 200	80.58 219	82.48 291	60.48 260	83.09 257	87.86 212	69.22 208	74.38 238	85.24 256	62.10 145	91.53 221	71.09 166	75.40 283	89.74 208

v8		79.97 145	79.02 146	82.80 167	84.09 253	64.50 196	87.96 135	90.29 142	74.13 121	75.24 223	86.81 213	62.88 133	93.89 132	74.39 136	75.40 283	90.00 195

Baseline_NR-MVSNet		78.15 188	78.33 161	77.61 270	85.79 225	56.21 313	86.78 171	85.76 247	73.60 132	77.93 158	87.57 193	65.02 111	88.99 268	67.14 207	75.33 285	87.63 258

pmmvs5		71.55 270	70.20 276	75.61 287	77.83 338	56.39 309	81.74 269	80.89 302	57.76 329	67.46 304	84.49 268	49.26 275	85.32 304	57.08 291	75.29 286	85.11 309

EPMVS		69.02 293	68.16 288	71.59 319	79.61 329	49.80 358	77.40 317	66.93 363	62.82 290	70.01 279	79.05 327	45.79 301	77.86 341	56.58 296	75.26 287	87.13 273

TranMVSNet+NR-MVSNet		80.84 117	80.31 116	82.42 177	87.85 182	62.33 236	87.74 144	91.33 112	80.55 8	77.99 157	89.86 129	65.23 109	92.62 182	67.05 208	75.24 288	92.30 113

test_fmvs2		68.35 300	67.48 300	70.98 326	69.50 366	51.95 344	80.05 291	76.38 339	49.33 355	74.65 235	84.38 271	23.30 366	75.40 357	74.51 134	75.17 289	85.60 300

tfpnnormal		74.39 244	73.16 248	78.08 262	86.10 223	58.05 281	84.65 224	87.53 219	70.32 185	71.22 268	85.63 248	54.97 208	89.86 253	43.03 356	75.02 290	86.32 287

COLMAP_ROB	66.92 17	73.01 261	70.41 273	80.81 215	87.13 209	65.63 170	88.30 124	84.19 268	62.96 286	63.80 335	87.69 190	38.04 341	92.56 185	46.66 344	74.91 291	84.24 317
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PatchT		68.46 299	67.85 293	70.29 328	80.70 314	43.93 371	72.47 339	74.88 344	60.15 310	70.55 270	76.57 344	49.94 265	81.59 324	50.58 321	74.83 292	85.34 303

pmmvs4		74.03 250	71.91 257	80.39 222	81.96 296	68.32 116	81.45 274	82.14 293	59.32 317	69.87 284	85.13 260	52.40 233	88.13 282	60.21 262	74.74 293	84.73 313

ITE_SJBPF				78.22 260	81.77 299	60.57 258		83.30 280	69.25 207	67.54 302	87.20 205	36.33 346	87.28 290	54.34 305	74.62 294	86.80 280

test0.0.03 1		68.00 301	67.69 297	68.90 333	77.55 339	47.43 360	75.70 327	72.95 352	66.66 243	66.56 313	82.29 301	48.06 284	75.87 354	44.97 353	74.51 295	83.41 326

test_0402		72.79 264	70.44 272	79.84 234	88.13 172	65.99 161	85.93 194	84.29 265	65.57 258	67.40 306	85.49 251	46.92 290	92.61 183	35.88 365	74.38 296	80.94 344

CP-MVSNet		78.22 184	78.34 160	77.84 265	87.83 184	54.54 328	87.94 137	91.17 116	77.65 37	73.48 244	88.49 170	62.24 143	88.43 278	62.19 244	74.07 297	90.55 169

FMVSNet5		69.50 290	67.96 291	74.15 303	82.97 280	55.35 320	80.01 292	82.12 294	62.56 293	63.02 336	81.53 307	36.92 344	81.92 323	48.42 334	74.06 298	85.17 308

MVS-HIRNet		59.14 327	57.67 330	63.57 344	81.65 300	43.50 372	71.73 341	65.06 368	39.59 366	51.43 365	57.73 370	38.34 339	82.58 322	39.53 362	73.95 299	64.62 366

tpmrst		72.39 265	72.13 256	73.18 311	80.54 316	49.91 356	79.91 294	79.08 323	63.11 283	71.69 264	79.95 322	55.32 206	82.77 321	65.66 219	73.89 300	86.87 278

PS-CasMVS		78.01 193	78.09 165	77.77 267	87.71 189	54.39 330	88.02 133	91.22 113	77.50 45	73.26 246	88.64 165	60.73 168	88.41 279	61.88 248	73.88 301	90.53 170

v148		78.72 174	77.80 174	81.47 194	82.73 284	61.96 242	86.30 185	88.08 205	73.26 139	76.18 199	85.47 252	62.46 138	92.36 193	71.92 160	73.82 302	90.09 189

Patchmatch-test		64.82 317	63.24 318	69.57 330	79.42 332	49.82 357	63.49 368	69.05 360	51.98 350	59.95 348	80.13 320	50.91 253	70.98 366	40.66 361	73.57 303	87.90 253

WR-MVS_H		78.51 179	78.49 155	78.56 255	88.02 178	56.38 310	88.43 117	92.67 61	77.14 53	73.89 241	87.55 195	66.25 98	89.24 264	58.92 273	73.55 304	90.06 193

AUN-MVS		79.21 162	77.60 182	84.05 118	88.71 155	67.61 131	85.84 198	87.26 225	69.08 214	77.23 172	88.14 184	53.20 229	93.47 151	75.50 129	73.45 305	91.06 149

hse-mvs2		81.72 99	80.94 105	84.07 115	88.72 154	67.68 130	85.87 196	87.26 225	76.02 82	84.67 54	88.22 179	61.54 152	93.48 150	82.71 60	73.44 306	91.06 149

testgi		66.67 308	66.53 306	67.08 340	75.62 348	41.69 375	75.93 323	76.50 338	66.11 250	65.20 327	86.59 224	35.72 348	74.71 359	43.71 354	73.38 307	84.84 311

Anonymous20240521		68.80 295	67.22 302	73.55 306	74.33 352	54.11 331	83.18 254	85.61 248	58.15 326	61.68 341	80.94 313	30.71 357	81.27 327	57.00 292	73.34 308	85.28 304

pm-mvs1		77.25 212	76.68 204	78.93 249	84.22 250	58.62 276	86.41 181	88.36 201	71.37 167	73.31 245	88.01 186	61.22 162	89.15 266	64.24 228	73.01 309	89.03 226

eth_miper_zixun_eth		77.92 195	76.69 203	81.61 192	83.00 278	61.98 241	83.15 255	89.20 173	69.52 202	74.86 232	84.35 272	61.76 148	92.56 185	71.50 163	72.89 310	90.28 180

miper_lstm_enhance		74.11 248	73.11 249	77.13 277	80.11 320	59.62 270	72.23 340	86.92 231	66.76 241	70.40 273	82.92 291	56.93 201	82.92 320	69.06 188	72.63 311	88.87 234

tpmvs		71.09 274	69.29 279	76.49 281	82.04 295	56.04 314	78.92 305	81.37 301	64.05 276	67.18 308	78.28 335	49.74 268	89.77 254	49.67 330	72.37 312	83.67 324

PEN-MVS		77.73 199	77.69 180	77.84 265	87.07 210	53.91 333	87.91 139	91.18 115	77.56 42	73.14 248	88.82 160	61.23 161	89.17 265	59.95 263	72.37 312	90.43 173

DSMNet-mixed		57.77 329	56.90 331	60.38 348	67.70 368	35.61 378	69.18 352	53.97 378	32.30 374	57.49 356	79.88 323	40.39 333	68.57 371	38.78 363	72.37 312	76.97 354

IterMVS-SCA-FT		75.43 238	73.87 241	80.11 229	82.69 285	64.85 189	81.57 272	83.47 278	69.16 212	70.49 272	84.15 275	51.95 242	88.15 281	69.23 185	72.14 315	87.34 266

tpm cat1		70.57 280	68.31 286	77.35 274	82.41 292	57.95 285	78.08 312	80.22 314	52.04 348	68.54 296	77.66 340	52.00 241	87.84 285	51.77 316	72.07 316	86.25 288

RPSCF		73.23 259	71.46 260	78.54 256	82.50 289	59.85 267	82.18 265	82.84 288	58.96 320	71.15 269	89.41 147	45.48 306	84.77 308	58.82 275	71.83 317	91.02 153

IterMVS		74.29 245	72.94 250	78.35 259	81.53 303	63.49 217	81.58 271	82.49 290	68.06 232	69.99 281	83.69 283	51.66 248	85.54 300	65.85 217	71.64 318	86.01 295
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AllTest		70.96 275	68.09 290	79.58 241	85.15 236	63.62 211	84.58 226	79.83 316	62.31 295	60.32 346	86.73 214	32.02 353	88.96 271	50.28 325	71.57 319	86.15 291

TestCases				79.58 241	85.15 236	63.62 211		79.83 316	62.31 295	60.32 346	86.73 214	32.02 353	88.96 271	50.28 325	71.57 319	86.15 291

baseline1		76.98 215	76.75 202	77.66 268	88.13 172	55.66 318	85.12 213	81.89 295	73.04 144	76.79 181	88.90 157	62.43 139	87.78 286	63.30 234	71.18 321	89.55 213

Patchmtry		70.74 278	69.16 281	75.49 290	80.72 313	54.07 332	74.94 335	80.30 312	58.34 324	70.01 279	81.19 308	52.50 231	86.54 293	53.37 310	71.09 322	85.87 299

DTE-MVSNet		76.99 214	76.80 198	77.54 272	86.24 220	53.06 341	87.52 148	90.66 128	77.08 56	72.50 254	88.67 164	60.48 175	89.52 259	57.33 289	70.74 323	90.05 194

MIMVSNet1		68.58 297	66.78 305	73.98 304	80.07 321	51.82 345	80.77 279	84.37 262	64.40 270	59.75 349	82.16 303	36.47 345	83.63 315	42.73 357	70.33 324	86.48 286

pmmvs6		74.69 243	73.39 245	78.61 253	81.38 306	57.48 293	86.64 175	87.95 209	64.99 265	70.18 276	86.61 223	50.43 260	89.52 259	62.12 246	70.18 325	88.83 236

test_vis1_rt		60.28 326	58.42 329	65.84 341	67.25 369	55.60 319	70.44 348	60.94 373	44.33 360	59.00 350	66.64 362	24.91 362	68.67 370	62.80 236	69.48 326	73.25 360

TinyColmap		67.30 305	64.81 309	74.76 297	81.92 298	56.68 305	80.29 289	81.49 300	60.33 307	56.27 360	83.22 287	24.77 363	87.66 288	45.52 350	69.47 327	79.95 348

OurMVSNet-221017-0		74.26 246	72.42 254	79.80 235	83.76 260	59.59 271	85.92 195	86.64 233	66.39 248	66.96 309	87.58 192	39.46 334	91.60 217	65.76 218	69.27 328	88.22 248

JIA-IIPM		66.32 311	62.82 322	76.82 279	77.09 342	61.72 246	65.34 364	75.38 342	58.04 328	64.51 329	62.32 365	42.05 326	86.51 294	51.45 319	69.22 329	82.21 336

ADS-MVSNet2		66.20 314	63.33 317	74.82 296	79.92 322	58.75 275	67.55 357	75.19 343	53.37 345	65.25 325	75.86 348	42.32 321	80.53 330	41.57 359	68.91 330	85.18 306

ADS-MVSNet		64.36 318	62.88 321	68.78 335	79.92 322	47.17 361	67.55 357	71.18 353	53.37 345	65.25 325	75.86 348	42.32 321	73.99 362	41.57 359	68.91 330	85.18 306

test20.03		67.45 303	66.95 304	68.94 332	75.48 349	44.84 369	77.50 316	77.67 329	66.66 243	63.01 337	83.80 280	47.02 289	78.40 337	42.53 358	68.86 332	83.58 325

EU-MVSNet		68.53 298	67.61 298	71.31 324	78.51 337	47.01 362	84.47 228	84.27 266	42.27 362	66.44 318	84.79 266	40.44 332	83.76 313	58.76 276	68.54 333	83.17 328

dmvs_testset		62.63 322	64.11 313	58.19 350	78.55 336	24.76 385	75.28 329	65.94 366	67.91 233	60.34 345	76.01 347	53.56 225	73.94 363	31.79 368	67.65 334	75.88 357

our_test_3		69.14 292	67.00 303	75.57 288	79.80 326	58.80 274	77.96 313	77.81 328	59.55 315	62.90 339	78.25 336	47.43 286	83.97 312	51.71 317	67.58 335	83.93 322

ppachtmachnet_test		70.04 286	67.34 301	78.14 261	79.80 326	61.13 250	79.19 301	80.59 307	59.16 319	65.27 324	79.29 326	46.75 292	87.29 289	49.33 331	66.72 336	86.00 297

LF4IMVS		64.02 319	62.19 323	69.50 331	70.90 364	53.29 340	76.13 321	77.18 335	52.65 347	58.59 351	80.98 312	23.55 365	76.52 348	53.06 312	66.66 337	78.68 351

Patchmatch-RL test		70.24 284	67.78 296	77.61 270	77.43 340	59.57 272	71.16 343	70.33 354	62.94 287	68.65 294	72.77 355	50.62 257	85.49 301	69.58 183	66.58 338	87.77 256

dp		66.80 306	65.43 308	70.90 327	79.74 328	48.82 359	75.12 333	74.77 345	59.61 314	64.08 332	77.23 341	42.89 317	80.72 329	48.86 333	66.58 338	83.16 329

test_fmvs3		63.36 321	61.82 324	67.98 337	62.51 373	46.96 363	77.37 318	74.03 349	45.24 358	67.50 303	78.79 332	12.16 377	72.98 365	72.77 154	66.02 340	83.99 321

CL-MVSNet_self_test		72.37 267	71.46 260	75.09 293	79.49 331	53.53 335	80.76 280	85.01 255	69.12 213	70.51 271	82.05 304	57.92 190	84.13 311	52.27 315	66.00 341	87.60 259

FPMVS		53.68 332	51.64 334	59.81 349	65.08 371	51.03 351	69.48 351	69.58 358	41.46 363	40.67 369	72.32 356	16.46 373	70.00 369	24.24 376	65.42 342	58.40 371

pmmvs-eth3d		70.50 282	67.83 294	78.52 257	77.37 341	66.18 157	81.82 267	81.51 299	58.90 321	63.90 334	80.42 318	42.69 319	86.28 296	58.56 277	65.30 343	83.11 330

N_pmnet		52.79 334	53.26 333	51.40 358	78.99 335	7.68 389	69.52 350	3.89 389	51.63 351	57.01 357	74.98 352	40.83 331	65.96 373	37.78 364	64.67 344	80.56 347

PM-MVS		66.41 310	64.14 312	73.20 310	73.92 354	56.45 307	78.97 304	64.96 369	63.88 280	64.72 328	80.24 319	19.84 369	83.44 317	66.24 211	64.52 345	79.71 349

KD-MVS_self_test		68.81 294	67.59 299	72.46 315	74.29 353	45.45 364	77.93 314	87.00 229	63.12 282	63.99 333	78.99 331	42.32 321	84.77 308	56.55 297	64.09 346	87.16 272

SixPastTwentyTwo		73.37 255	71.26 265	79.70 237	85.08 239	57.89 286	85.57 201	83.56 276	71.03 173	65.66 321	85.88 241	42.10 325	92.57 184	59.11 271	63.34 347	88.65 242

EGC-MVSNET		52.07 336	47.05 340	67.14 339	83.51 264	60.71 256	80.50 285	67.75 362	0.07 384	0.43 385	75.85 350	24.26 364	81.54 325	28.82 370	62.25 348	59.16 369

TransMVSNet (Re)		75.39 240	74.56 232	77.86 264	85.50 231	57.10 298	86.78 171	86.09 243	72.17 154	71.53 265	87.34 199	63.01 132	89.31 263	56.84 294	61.83 349	87.17 270

MDA-MVSNet_test_wron		65.03 315	62.92 319	71.37 321	75.93 344	56.73 302	69.09 355	74.73 346	57.28 333	54.03 363	77.89 337	45.88 299	74.39 361	49.89 329	61.55 350	82.99 333

YYNet1		65.03 315	62.91 320	71.38 320	75.85 346	56.60 306	69.12 354	74.66 348	57.28 333	54.12 362	77.87 338	45.85 300	74.48 360	49.95 328	61.52 351	83.05 331

mvsany_test1		62.30 323	61.26 327	65.41 342	69.52 365	54.86 325	66.86 359	49.78 380	46.65 357	68.50 297	83.21 288	49.15 276	66.28 372	56.93 293	60.77 352	75.11 358

ambc				75.24 292	73.16 359	50.51 354	63.05 369	87.47 221		64.28 330	77.81 339	17.80 371	89.73 256	57.88 284	60.64 353	85.49 301

TDRefinement		67.49 302	64.34 311	76.92 278	73.47 358	61.07 251	84.86 219	82.98 286	59.77 313	58.30 353	85.13 260	26.06 361	87.89 284	47.92 341	60.59 354	81.81 340

Gipuma		45.18 342	41.86 345	55.16 356	77.03 343	51.52 348	32.50 377	80.52 308	32.46 373	27.12 376	35.02 377	9.52 380	75.50 355	22.31 377	60.21 355	38.45 376
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
new-patchmatchnet		61.73 324	61.73 325	61.70 346	72.74 361	24.50 386	69.16 353	78.03 327	61.40 301	56.72 358	75.53 351	38.42 338	76.48 349	45.95 349	57.67 356	84.13 319

MDA-MVSNet-bldmvs		66.68 307	63.66 316	75.75 285	79.28 333	60.56 259	73.92 337	78.35 326	64.43 269	50.13 366	79.87 324	44.02 312	83.67 314	46.10 348	56.86 357	83.03 332

new_pmnet		50.91 337	50.29 337	52.78 357	68.58 367	34.94 380	63.71 366	56.63 377	39.73 365	44.95 367	65.47 363	21.93 367	58.48 376	34.98 366	56.62 358	64.92 365

test_f		52.09 335	50.82 336	55.90 354	53.82 380	42.31 374	59.42 370	58.31 376	36.45 369	56.12 361	70.96 359	12.18 376	57.79 377	53.51 309	56.57 359	67.60 363

test_vis3_rt		49.26 339	47.02 341	56.00 353	54.30 378	45.27 368	66.76 361	48.08 381	36.83 368	44.38 368	53.20 373	7.17 384	64.07 374	56.77 295	55.66 360	58.65 370

PMVS	37.38 22	44.16 343	40.28 346	55.82 355	40.82 386	42.54 373	65.12 365	63.99 370	34.43 371	24.48 377	57.12 372	3.92 387	76.17 353	17.10 379	55.52 361	48.75 374
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
APD_test1		53.31 333	49.93 338	63.42 345	65.68 370	50.13 355	71.59 342	66.90 364	34.43 371	40.58 370	71.56 358	8.65 382	76.27 351	34.64 367	55.36 362	63.86 367

pmmvs3		57.79 328	54.26 332	68.37 336	64.02 372	56.72 303	75.12 333	65.17 367	40.20 364	52.93 364	69.86 361	20.36 368	75.48 356	45.45 351	55.25 363	72.90 361

UnsupCasMVSNet_eth		67.33 304	65.99 307	71.37 321	73.48 357	51.47 349	75.16 331	85.19 252	65.20 260	60.78 344	80.93 315	42.35 320	77.20 343	57.12 290	53.69 364	85.44 302

K. test v3		71.19 272	68.51 284	79.21 247	83.04 277	57.78 289	84.35 235	76.91 337	72.90 147	62.99 338	82.86 293	39.27 335	91.09 237	61.65 251	52.66 365	88.75 239

UnsupCasMVSNet_bld		63.70 320	61.53 326	70.21 329	73.69 356	51.39 350	72.82 338	81.89 295	55.63 340	57.81 355	71.80 357	38.67 337	78.61 336	49.26 332	52.21 366	80.63 345

LCM-MVSNet		54.25 330	49.68 339	67.97 338	53.73 381	45.28 367	66.85 360	80.78 304	35.96 370	39.45 371	62.23 366	8.70 381	78.06 340	48.24 338	51.20 367	80.57 346

KD-MVS_2432*1600		66.22 312	63.89 314	73.21 308	75.47 350	53.42 337	70.76 346	84.35 263	64.10 274	66.52 315	78.52 333	34.55 350	84.98 305	50.40 323	50.33 368	81.23 342

miper_refine_blended		66.22 312	63.89 314	73.21 308	75.47 350	53.42 337	70.76 346	84.35 263	64.10 274	66.52 315	78.52 333	34.55 350	84.98 305	50.40 323	50.33 368	81.23 342

mvsany_test3		53.99 331	51.45 335	61.61 347	55.51 377	44.74 370	63.52 367	45.41 384	43.69 361	58.11 354	76.45 345	17.99 370	63.76 375	54.77 303	47.59 370	76.34 356

lessismore_v0				78.97 248	81.01 312	57.15 297		65.99 365		61.16 343	82.82 294	39.12 336	91.34 228	59.67 265	46.92 371	88.43 246

testf1		45.72 340	41.96 343	57.00 351	56.90 375	45.32 365	66.14 362	59.26 374	26.19 375	30.89 374	60.96 368	4.14 385	70.64 367	26.39 374	46.73 372	55.04 372

APD_test2		45.72 340	41.96 343	57.00 351	56.90 375	45.32 365	66.14 362	59.26 374	26.19 375	30.89 374	60.96 368	4.14 385	70.64 367	26.39 374	46.73 372	55.04 372

PVSNet_0	57.27 20	61.67 325	59.27 328	68.85 334	79.61 329	57.44 294	68.01 356	73.44 351	55.93 339	58.54 352	70.41 360	44.58 309	77.55 342	47.01 343	35.91 374	71.55 362

test_method		31.52 346	29.28 350	38.23 361	27.03 388	6.50 390	20.94 379	62.21 372	4.05 382	22.35 380	52.50 374	13.33 374	47.58 381	27.04 373	34.04 375	60.62 368

PMMVS2		40.82 344	38.86 347	46.69 359	53.84 379	16.45 387	48.61 374	49.92 379	37.49 367	31.67 372	60.97 367	8.14 383	56.42 378	28.42 371	30.72 376	67.19 364

DeepMVS_CX				27.40 364	40.17 387	26.90 383		24.59 388	17.44 380	23.95 378	48.61 375	9.77 379	26.48 383	18.06 378	24.47 377	28.83 377

MVE	26.22 23	30.37 348	25.89 352	43.81 360	44.55 385	35.46 379	28.87 378	39.07 385	18.20 379	18.58 381	40.18 376	2.68 388	47.37 382	17.07 380	23.78 378	48.60 375
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		31.77 345	30.64 348	35.15 362	52.87 382	27.67 382	57.09 372	47.86 382	24.64 377	16.40 382	33.05 378	11.23 378	54.90 379	14.46 381	18.15 379	22.87 378

EMVS		30.81 347	29.65 349	34.27 363	50.96 383	25.95 384	56.58 373	46.80 383	24.01 378	15.53 383	30.68 379	12.47 375	54.43 380	12.81 382	17.05 380	22.43 379

ANet_high		50.57 338	46.10 342	63.99 343	48.67 384	39.13 376	70.99 345	80.85 303	61.39 302	31.18 373	57.70 371	17.02 372	73.65 364	31.22 369	15.89 381	79.18 350

tmp_tt		18.61 350	21.40 353	10.23 366	4.82 389	10.11 388	34.70 376	30.74 387	1.48 383	23.91 379	26.07 380	28.42 359	13.41 385	27.12 372	15.35 382	7.17 380

wuyk23d		16.82 351	15.94 354	19.46 365	58.74 374	31.45 381	39.22 375	3.74 390	6.84 381	6.04 384	2.70 384	1.27 389	24.29 384	10.54 383	14.40 383	2.63 381

testmvs		6.04 354	8.02 357	0.10 368	0.08 390	0.03 392	69.74 349	0.04 391	0.05 385	0.31 386	1.68 385	0.02 391	0.04 386	0.24 384	0.02 384	0.25 383

test123		6.12 353	8.11 356	0.14 367	0.06 391	0.09 391	71.05 344	0.03 392	0.04 386	0.25 387	1.30 386	0.05 390	0.03 387	0.21 385	0.01 385	0.29 382

test_blank		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet_test		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

DCPMVS		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

cdsmvs_eth3d_5k		19.96 349	26.61 351	0.00 369	0.00 392	0.00 393	0.00 380	89.26 169	0.00 387	0.00 388	88.61 166	61.62 151	0.00 388	0.00 386	0.00 386	0.00 384

pcd_1.5k_mvsjas		5.26 355	7.02 358	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	63.15 128	0.00 388	0.00 386	0.00 386	0.00 384

sosnet-low-res		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

sosnet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uncertanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

Regformer		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

ab-mvs-re		7.23 352	9.64 355	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	86.72 216	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

FOURS1					95.00 10	72.39 38	95.06 1	93.84 15	74.49 112	91.30 15

test_one_0601					95.07 7	71.46 54		94.14 5	78.27 34	92.05 11	95.74 6	80.83 11

eth-test2					0.00 392

eth-test					0.00 392

test_241102_ONE					95.30 2	70.98 62		94.06 10	77.17 52	93.10 1	95.39 11	82.99 1	97.27 10

save fliter					93.80 40	72.35 41	90.47 63	91.17 116	74.31 115

test0726					95.27 5	71.25 56	93.60 6	94.11 6	77.33 47	92.81 3	95.79 3	80.98 9

GSMVS																88.96 231

test_part2					95.06 8	72.65 31				91.80 13

sam_mvs1												51.32 250				88.96 231

sam_mvs												50.01 263

MTGPA								92.02 85

test_post1							78.90 306				5.43 383	48.81 283	85.44 303	59.25 269

test_post											5.46 382	50.36 261	84.24 310

patchmatchnet-post											74.00 353	51.12 252	88.60 276

MTMP							92.18 34	32.83 386

gm-plane-assit					81.40 305	53.83 334			62.72 292		80.94 313		92.39 191	63.40 233

TEST9					93.26 50	72.96 24	88.75 107	91.89 93	68.44 228	85.00 47	93.10 57	74.36 28	95.41 66

test_8					93.13 52	72.57 34	88.68 112	91.84 97	68.69 223	84.87 51	93.10 57	74.43 26	95.16 75

agg_prior					92.85 59	71.94 50		91.78 100		84.41 61			94.93 86

test_prior4						72.60 33	89.01 97

test_prior				86.33 53	92.61 65	69.59 87		92.97 50					95.48 61			93.91 51

旧先验2							86.56 178		58.10 327	87.04 31			88.98 269	74.07 139

新几何2							86.29 186

无先验							87.48 149	88.98 182	60.00 311				94.12 120	67.28 204		88.97 230

原ACMM2							86.86 167

testdata2													91.01 239	62.37 243

segment_acmp												73.08 37

testdata1							84.14 239		75.71 86

plane_prior7					90.08 102	68.51 114

plane_prior6					89.84 111	68.70 109						60.42 176

plane_prior4											91.00 110

plane_prior3						68.60 112			78.44 30	78.92 131

plane_prior2							91.25 49		79.12 22

plane_prior1					89.90 110

n2								0.00 393

nn								0.00 393

door-mid								69.98 356

test11								92.23 79

door								69.44 359

HQP5-MVS						66.98 145

HQP-NCC					89.33 127		89.17 90		76.41 71	77.23 172

ACMP_Plane					89.33 127		89.17 90		76.41 71	77.23 172

BP-MVS														77.47 104

HQP4-MVS										77.24 171			95.11 79			91.03 151

HQP2-MVS												60.17 179

NP-MVS					89.62 114	68.32 116					90.24 122

MDTV_nov1_ep13_2view						37.79 377	75.16 331		55.10 341	66.53 314		49.34 273		53.98 306		87.94 252

Test By Simon												64.33 115

High-resolution multi-view benchmark