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 27	92.85 54	80.26 11	87.78 29	94.27 32	75.89 19	96.81 23	87.45 32	96.44 9	93.05 96

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 45					97.53 2	89.67 6	96.44 9	94.41 32

No_MVS				89.16 1	94.34 27	75.53 2		92.99 45					97.53 2	89.67 6	96.44 9	94.41 32

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 44	82.45 3	96.87 20	83.77 58	96.48 8	94.88 14

MTAPA		87.23 28	87.00 29	87.90 22	94.18 35	74.25 5	86.58 187	92.02 85	79.45 19	85.88 46	94.80 17	68.07 89	96.21 42	86.69 36	95.34 33	93.23 87

MP-MVS		87.71 20	87.64 22	87.93 21	94.36 26	73.88 6	92.71 22	92.65 64	77.57 41	83.84 82	94.40 30	72.24 43	96.28 40	85.65 38	95.30 35	93.62 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		87.11 30	86.92 32	87.68 34	94.20 34	73.86 7	93.98 3	92.82 58	76.62 70	83.68 84	94.46 25	67.93 90	95.95 52	84.20 55	94.39 53	93.23 87

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 61	93.00 43	80.90 7	88.06 26	94.06 42	76.43 16	96.84 21	88.48 24	95.99 18	94.34 37

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 24	93.63 21	74.77 107	92.29 7	95.97 2	74.28 29	97.24 12	88.58 21	96.91 1	94.87 16
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 90	73.65 10	92.66 23	91.17 116	86.57 1	87.39 35	94.97 16	71.70 50	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 52	92.83 55	81.50 5	85.79 48	93.47 60	73.02 39	97.00 18	84.90 42	94.94 39	94.10 45

ACMMPR		87.44 23	87.23 27	88.08 14	94.64 13	73.59 12	93.04 12	93.20 34	76.78 65	84.66 66	94.52 21	68.81 84	96.65 30	84.53 49	94.90 40	94.00 50

region2R		87.42 25	87.20 28	88.09 13	94.63 14	73.55 13	93.03 14	93.12 37	76.73 68	84.45 70	94.52 21	69.09 78	96.70 27	84.37 51	94.83 44	94.03 49

mPP-MVS		86.67 37	86.32 39	87.72 30	94.41 22	73.55 13	92.74 20	92.22 80	76.87 62	82.81 97	94.25 34	66.44 105	96.24 41	82.88 67	94.28 56	93.38 81

HFP-MVS		87.58 22	87.47 24	87.94 19	94.58 16	73.54 15	93.04 12	93.24 33	76.78 65	84.91 59	94.44 28	70.78 60	96.61 32	84.53 49	94.89 41	93.66 65

3Dnovator+	77.84 4	85.48 54	84.47 69	88.51 7	91.08 81	73.49 16	93.18 11	93.78 18	80.79 8	76.66 195	93.37 62	60.40 188	96.75 26	77.20 117	93.73 62	95.29 5

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 16	94.11 6	80.27 10	91.35 14	94.16 37	78.35 13	96.77 24	89.59 8	94.22 58	94.67 24
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 36	86.27 40	87.90 22	94.22 33	73.38 18	90.22 70	93.04 38	75.53 91	83.86 81	94.42 29	67.87 92	96.64 31	82.70 72	94.57 49	93.66 65

ZNCC-MVS		87.94 19	87.85 20	88.20 12	94.39 24	73.33 19	93.03 14	93.81 17	76.81 63	85.24 53	94.32 31	71.76 48	96.93 19	85.53 39	95.79 22	94.32 38

XVS		87.18 29	86.91 33	88.00 17	94.42 20	73.33 19	92.78 18	92.99 45	79.14 21	83.67 85	94.17 36	67.45 95	96.60 33	83.06 63	94.50 50	94.07 47

X-MVStestdata		80.37 145	77.83 182	88.00 17	94.42 20	73.33 19	92.78 18	92.99 45	79.14 21	83.67 85	12.47 399	67.45 95	96.60 33	83.06 63	94.50 50	94.07 47

ACMMP_NAP		88.05 17	88.08 17	87.94 19	93.70 41	73.05 22	90.86 56	93.59 23	76.27 79	88.14 24	95.09 15	71.06 57	96.67 29	87.67 29	96.37 14	94.09 46

DPM-MVS		84.93 63	84.29 70	86.84 47	90.20 100	73.04 23	87.12 169	93.04 38	69.80 205	82.85 95	91.22 110	73.06 38	96.02 47	76.72 126	94.63 47	91.46 148

GST-MVS		87.42 25	87.26 25	87.89 24	94.12 36	72.97 24	92.39 26	93.43 28	76.89 61	84.68 63	93.99 48	70.67 62	96.82 22	84.18 56	95.01 37	93.90 55

TEST9					93.26 50	72.96 25	88.75 115	91.89 93	68.44 239	85.00 57	93.10 67	74.36 28	95.41 67

train_agg		86.43 39	86.20 41	87.13 44	93.26 50	72.96 25	88.75 115	91.89 93	68.69 234	85.00 57	93.10 67	74.43 26	95.41 67	84.97 41	95.71 25	93.02 98

SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 69	72.96 25	93.73 5	93.67 20	80.19 12	88.10 25	94.80 17	73.76 33	97.11 15	87.51 31	95.82 21	94.90 13
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator	76.31 5	83.38 85	82.31 95	86.59 52	87.94 181	72.94 28	90.64 59	92.14 84	77.21 52	75.47 220	92.83 76	58.56 195	94.72 99	73.24 159	92.71 69	92.13 130

SD-MVS		88.06 15	88.50 14	86.71 51	92.60 66	72.71 29	91.81 42	93.19 35	77.87 36	90.32 17	94.00 46	74.83 23	93.78 136	87.63 30	94.27 57	93.65 69
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 60	84.75 64	86.32 55	91.65 76	72.70 30	85.98 202	90.33 141	76.11 81	82.08 102	91.61 100	71.36 56	94.17 120	81.02 82	92.58 70	92.08 131

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 43	94.10 8	75.90 85	92.29 7	95.66 10	81.67 6	97.38 10	87.44 33	96.34 15	93.95 52
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 48	85.39 54	87.38 39	93.59 45	72.63 33	92.74 20	93.18 36	76.78 65	80.73 121	93.82 53	64.33 125	96.29 39	82.67 73	90.69 94	93.23 87
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	89.01 105

test_8					93.13 52	72.57 35	88.68 120	91.84 97	68.69 234	84.87 61	93.10 67	74.43 26	95.16 76

TSAR-MVS + GP.		85.71 51	85.33 56	86.84 47	91.34 78	72.50 36	89.07 104	87.28 228	76.41 72	85.80 47	90.22 134	74.15 31	95.37 72	81.82 77	91.88 78	92.65 109

CSCG		86.41 41	86.19 42	87.07 45	92.91 58	72.48 37	90.81 57	93.56 24	73.95 123	83.16 91	91.07 116	75.94 18	95.19 75	79.94 94	94.38 54	93.55 76

MCST-MVS		87.37 27	87.25 26	87.73 28	94.53 17	72.46 38	89.82 77	93.82 16	73.07 147	84.86 62	92.89 74	76.22 17	96.33 38	84.89 44	95.13 36	94.40 34

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 113	91.30 15

APD-MVS		87.44 23	87.52 23	87.19 42	94.24 32	72.39 39	91.86 41	92.83 55	73.01 149	88.58 21	94.52 21	73.36 34	96.49 36	84.26 52	95.01 37	92.70 105
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepC-MVS_fast	79.65 3	86.91 33	86.62 36	87.76 27	93.52 46	72.37 41	91.26 48	93.04 38	76.62 70	84.22 74	93.36 63	71.44 54	96.76 25	80.82 85	95.33 34	94.16 43
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 42	90.47 64	91.17 116	74.31 116

DeepC-MVS	79.81 2	87.08 32	86.88 34	87.69 33	91.16 80	72.32 43	90.31 68	93.94 14	77.12 55	82.82 96	94.23 35	72.13 45	97.09 16	84.83 45	95.37 32	93.65 69
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 44		92.67 61	70.98 180	87.75 31	94.07 41	74.01 32	96.70 27	84.66 47	94.84 43

HPM-MVS		87.11 30	86.98 30	87.50 38	93.88 39	72.16 45	92.19 34	93.33 31	76.07 82	83.81 83	93.95 51	69.77 72	96.01 48	85.15 40	94.66 46	94.32 38
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 16	87.72 30	93.68 43	72.13 46	91.41 47	92.35 74	74.62 111	88.90 20	93.85 52	75.75 20	96.00 49	87.80 28	94.63 47	95.04 7
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 34	86.67 35	86.91 46	94.11 37	72.11 47	92.37 28	92.56 67	74.50 112	86.84 42	94.65 20	67.31 97	95.77 54	84.80 46	92.85 67	92.84 103

MVS_0304		88.08 14	88.08 17	88.08 14	89.67 114	72.04 48	92.26 33	89.26 173	84.19 2	85.01 55	95.18 13	69.93 69	97.20 14	91.63 2	95.60 29	94.99 9

MP-MVS-pluss		87.67 21	87.72 21	87.54 36	93.64 44	72.04 48	89.80 79	93.50 25	75.17 100	86.34 44	95.29 12	70.86 59	96.00 49	88.78 19	96.04 16	94.58 27
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SF-MVS		88.46 12	88.74 12	87.64 35	92.78 61	71.95 50	92.40 24	94.74 2	75.71 87	89.16 19	95.10 14	75.65 21	96.19 43	87.07 34	96.01 17	94.79 21

agg_prior					92.85 59	71.94 51		91.78 100		84.41 71			94.93 87

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 52	93.83 4	93.96 13	75.70 89	91.06 16	96.03 1	76.84 14	97.03 17	89.09 11	95.65 27	94.47 31
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MVS_111021_LR		82.61 97	82.11 97	84.11 117	88.82 149	71.58 53	85.15 222	86.16 247	74.69 108	80.47 123	91.04 117	62.29 151	90.55 256	80.33 91	90.08 104	90.20 193

MAR-MVS		81.84 107	80.70 118	85.27 74	91.32 79	71.53 54	89.82 77	90.92 122	69.77 207	78.50 151	86.21 245	62.36 150	94.52 106	65.36 230	92.05 77	89.77 218
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 55		94.14 5	78.27 35	92.05 11	95.74 6	80.83 11

test_0728_SECOND				87.71 32	95.34 1	71.43 56	93.49 9	94.23 3					97.49 4	89.08 12	96.41 12	94.21 42

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 57	95.06 1	94.23 3	78.38 33	92.78 4	95.74 6	82.45 3	97.49 4	89.42 9	96.68 2	94.95 10

IU-MVS					95.30 2	71.25 57		92.95 51	66.81 252	92.39 6				88.94 16	96.63 4	94.85 19

DVP-MVS		89.60 3	90.35 3	87.33 40	95.27 5	71.25 57	93.49 9	92.73 59	77.33 48	92.12 9	95.78 4	80.98 9	97.40 8	89.08 12	96.41 12	93.33 84
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 57	93.60 6	94.11 6	77.33 48	92.81 3	95.79 3	80.98 9

CDPH-MVS		85.76 50	85.29 59	87.17 43	93.49 47	71.08 61	88.58 123	92.42 72	68.32 241	84.61 67	93.48 58	72.32 42	96.15 45	79.00 98	95.43 31	94.28 40

CNLPA		78.08 199	76.79 209	81.97 195	90.40 97	71.07 62	87.59 157	84.55 266	66.03 268	72.38 270	89.64 145	57.56 204	86.04 309	59.61 276	83.35 196	88.79 250

SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 63	93.57 7	94.06 10	77.24 50	93.10 1	95.72 8	82.99 1	97.44 6	89.07 14	96.63 4	94.88 14

test_241102_ONE					95.30 2	70.98 63		94.06 10	77.17 53	93.10 1	95.39 11	82.99 1	97.27 11

PHI-MVS		86.43 39	86.17 43	87.24 41	90.88 87	70.96 65	92.27 32	94.07 9	72.45 152	85.22 54	91.90 92	69.47 74	96.42 37	83.28 62	95.94 19	94.35 36

OPM-MVS		83.50 81	82.95 86	85.14 77	88.79 152	70.95 66	89.13 103	91.52 106	77.55 44	80.96 119	91.75 95	60.71 179	94.50 107	79.67 95	86.51 149	89.97 210
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CANet		86.45 38	86.10 45	87.51 37	90.09 102	70.94 67	89.70 83	92.59 66	81.78 4	81.32 112	91.43 106	70.34 64	97.23 13	84.26 52	93.36 64	94.37 35

DP-MVS Recon		83.11 91	82.09 98	86.15 58	94.44 19	70.92 68	88.79 113	92.20 81	70.53 189	79.17 137	91.03 119	64.12 127	96.03 46	68.39 206	90.14 102	91.50 145

CPTT-MVS		83.73 74	83.33 80	84.92 87	93.28 49	70.86 69	92.09 37	90.38 137	68.75 233	79.57 132	92.83 76	60.60 184	93.04 178	80.92 84	91.56 84	90.86 167

h-mvs33		83.15 88	82.19 96	86.02 61	90.56 93	70.85 70	88.15 140	89.16 178	76.02 83	84.67 64	91.39 107	61.54 162	95.50 61	82.71 70	75.48 294	91.72 139

新几何1				83.42 147	93.13 52	70.71 71		85.48 256	57.43 350	81.80 107	91.98 90	63.28 133	92.27 201	64.60 237	92.99 65	87.27 280

test12				86.80 49	92.63 64	70.70 72		91.79 99		82.71 98		71.67 51	96.16 44		94.50 50	93.54 77

SR-MVS-dyc-post		85.77 49	85.61 52	86.23 56	93.06 55	70.63 73	91.88 39	92.27 76	73.53 136	85.69 49	94.45 26	65.00 123	95.56 58	82.75 68	91.87 79	92.50 114

RE-MVS-def			85.48 53		93.06 55	70.63 73	91.88 39	92.27 76	73.53 136	85.69 49	94.45 26	63.87 129		82.75 68	91.87 79	92.50 114

HPM-MVS_fast		85.35 58	84.95 63	86.57 53	93.69 42	70.58 75	92.15 36	91.62 103	73.89 126	82.67 99	94.09 40	62.60 144	95.54 60	80.93 83	92.93 66	93.57 74

MSLP-MVS++		85.43 56	85.76 50	84.45 103	91.93 72	70.24 76	90.71 58	92.86 53	77.46 47	84.22 74	92.81 78	67.16 99	92.94 180	80.36 90	94.35 55	90.16 194

MVSFormer		82.85 94	82.05 99	85.24 75	87.35 203	70.21 77	90.50 62	90.38 137	68.55 236	81.32 112	89.47 151	61.68 159	93.46 153	78.98 99	90.26 100	92.05 132

lupinMVS		81.39 119	80.27 128	84.76 93	87.35 203	70.21 77	85.55 215	86.41 242	62.85 303	81.32 112	88.61 176	61.68 159	92.24 203	78.41 106	90.26 100	91.83 136

xiu_mvs_v1_base_debu		80.80 131	79.72 137	84.03 130	87.35 203	70.19 79	85.56 212	88.77 194	69.06 226	81.83 104	88.16 190	50.91 265	92.85 182	78.29 108	87.56 132	89.06 234

xiu_mvs_v1_base		80.80 131	79.72 137	84.03 130	87.35 203	70.19 79	85.56 212	88.77 194	69.06 226	81.83 104	88.16 190	50.91 265	92.85 182	78.29 108	87.56 132	89.06 234

xiu_mvs_v1_base_debi		80.80 131	79.72 137	84.03 130	87.35 203	70.19 79	85.56 212	88.77 194	69.06 226	81.83 104	88.16 190	50.91 265	92.85 182	78.29 108	87.56 132	89.06 234

API-MVS		81.99 105	81.23 109	84.26 114	90.94 85	70.18 82	91.10 53	89.32 169	71.51 169	78.66 147	88.28 186	65.26 118	95.10 83	64.74 236	91.23 88	87.51 274

test_fmvsm_n_1920		85.29 59	85.34 55	85.13 79	86.12 228	69.93 83	88.65 121	90.78 127	69.97 201	88.27 23	93.98 49	71.39 55	91.54 228	88.49 23	90.45 97	93.91 53

OpenMVS	72.83 10	79.77 156	78.33 171	84.09 121	85.17 242	69.91 84	90.57 60	90.97 121	66.70 255	72.17 272	91.91 91	54.70 224	93.96 124	61.81 260	90.95 91	88.41 259

jason		81.39 119	80.29 127	84.70 94	86.63 222	69.90 85	85.95 203	86.77 238	63.24 296	81.07 118	89.47 151	61.08 175	92.15 205	78.33 107	90.07 105	92.05 132
jason: jason.
MVP-Stereo		76.12 238	74.46 245	81.13 217	85.37 240	69.79 86	84.42 243	87.95 213	65.03 278	67.46 318	85.33 264	53.28 239	91.73 221	58.01 293	83.27 197	81.85 355
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PVSNet_Blended_VisFu		82.62 96	81.83 104	84.96 84	90.80 89	69.76 87	88.74 117	91.70 102	69.39 213	78.96 139	88.46 181	65.47 117	94.87 94	74.42 145	88.57 123	90.24 192

test_prior				86.33 54	92.61 65	69.59 88		92.97 50					95.48 62			93.91 53

APD-MVS_3200maxsize		85.97 45	85.88 48	86.22 57	92.69 63	69.53 89	91.93 38	92.99 45	73.54 135	85.94 45	94.51 24	65.80 115	95.61 57	83.04 65	92.51 71	93.53 78

test_fmvsmconf_n		85.92 46	86.04 47	85.57 68	85.03 249	69.51 90	89.62 86	90.58 131	73.42 138	87.75 31	94.02 44	72.85 40	93.24 160	90.37 3	90.75 93	93.96 51

EPNet		83.72 75	82.92 87	86.14 59	84.22 263	69.48 91	91.05 55	85.27 257	81.30 6	76.83 190	91.65 97	66.09 110	95.56 58	76.00 132	93.85 60	93.38 81
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ET-MVSNet_ETH3D		78.63 186	76.63 215	84.64 95	86.73 220	69.47 92	85.01 225	84.61 265	69.54 211	66.51 333	86.59 234	50.16 274	91.75 219	76.26 128	84.24 180	92.69 107

alignmvs		85.48 54	85.32 57	85.96 62	89.51 120	69.47 92	89.74 81	92.47 68	76.17 80	87.73 33	91.46 105	70.32 65	93.78 136	81.51 78	88.95 117	94.63 26

DP-MVS		76.78 228	74.57 241	83.42 147	93.29 48	69.46 94	88.55 124	83.70 279	63.98 293	70.20 288	88.89 168	54.01 232	94.80 96	46.66 355	81.88 215	86.01 307

canonicalmvs		85.91 47	85.87 49	86.04 60	89.84 112	69.44 95	90.45 66	93.00 43	76.70 69	88.01 28	91.23 109	73.28 36	93.91 131	81.50 79	88.80 120	94.77 22

test_fmvsmconf0.1_n		85.61 53	85.65 51	85.50 69	82.99 294	69.39 96	89.65 84	90.29 144	73.31 141	87.77 30	94.15 38	71.72 49	93.23 161	90.31 4	90.67 95	93.89 56

test_fmvsmvis_n_1920		84.02 70	83.87 72	84.49 101	84.12 265	69.37 97	88.15 140	87.96 212	70.01 199	83.95 80	93.23 65	68.80 85	91.51 231	88.61 20	89.96 106	92.57 110

nrg030		83.88 71	83.53 75	84.96 84	86.77 219	69.28 98	90.46 65	92.67 61	74.79 106	82.95 92	91.33 108	72.70 41	93.09 174	80.79 87	79.28 247	92.50 114

test_fmvsmconf0.01_n		84.73 66	84.52 68	85.34 72	80.25 334	69.03 99	89.47 88	89.65 161	73.24 144	86.98 40	94.27 32	66.62 101	93.23 161	90.26 5	89.95 107	93.78 62

DeepPCF-MVS	80.84 1	88.10 13	88.56 13	86.73 50	92.24 68	69.03 99	89.57 87	93.39 30	77.53 45	89.79 18	94.12 39	78.98 12	96.58 35	85.66 37	95.72 24	94.58 27

XVG-OURS		80.41 142	79.23 150	83.97 134	85.64 234	69.02 101	83.03 271	90.39 136	71.09 177	77.63 173	91.49 104	54.62 226	91.35 237	75.71 134	83.47 194	91.54 142

PCF-MVS	73.52 7	80.38 143	78.84 159	85.01 82	87.71 192	68.99 102	83.65 255	91.46 111	63.00 300	77.77 171	90.28 131	66.10 109	95.09 84	61.40 263	88.22 129	90.94 165
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
QAPM		80.88 126	79.50 142	85.03 81	88.01 180	68.97 103	91.59 43	92.00 87	66.63 261	75.15 235	92.16 88	57.70 202	95.45 63	63.52 240	88.76 121	90.66 174

AdaColmap		80.58 140	79.42 143	84.06 125	93.09 54	68.91 104	89.36 94	88.97 188	69.27 216	75.70 217	89.69 143	57.20 209	95.77 54	63.06 245	88.41 127	87.50 275

fmvsm_l_conf0.5_n		84.47 67	84.54 66	84.27 113	85.42 238	68.81 105	88.49 125	87.26 229	68.08 243	88.03 27	93.49 57	72.04 46	91.77 218	88.90 17	89.14 116	92.24 125

原ACMM1				84.35 107	93.01 57	68.79 106		92.44 69	63.96 294	81.09 117	91.57 101	66.06 111	95.45 63	67.19 216	94.82 45	88.81 249

XVG-OURS-SEG-HR		80.81 129	79.76 136	83.96 135	85.60 235	68.78 107	83.54 260	90.50 134	70.66 187	76.71 194	91.66 96	60.69 180	91.26 239	76.94 120	81.58 218	91.83 136

LPG-MVS_test		82.08 102	81.27 108	84.50 99	89.23 135	68.76 108	90.22 70	91.94 91	75.37 94	76.64 196	91.51 102	54.29 228	94.91 88	78.44 104	83.78 183	89.83 215

LGP-MVS_train				84.50 99	89.23 135	68.76 108		91.94 91	75.37 94	76.64 196	91.51 102	54.29 228	94.91 88	78.44 104	83.78 183	89.83 215

Effi-MVS+-dtu		80.03 152	78.57 164	84.42 104	85.13 246	68.74 110	88.77 114	88.10 208	74.99 102	74.97 240	83.49 297	57.27 208	93.36 156	73.53 153	80.88 225	91.18 154

Vis-MVSNet		83.46 82	82.80 89	85.43 71	90.25 99	68.74 110	90.30 69	90.13 148	76.33 78	80.87 120	92.89 74	61.00 176	94.20 118	72.45 168	90.97 90	93.35 83
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
HQP_MVS		83.64 77	83.14 81	85.14 77	90.08 103	68.71 112	91.25 50	92.44 69	79.12 23	78.92 141	91.00 120	60.42 186	95.38 69	78.71 102	86.32 151	91.33 149

plane_prior						68.71 112	90.38 67		77.62 39						86.16 155

plane_prior6					89.84 112	68.70 114						60.42 186

ACMP	74.13 6	81.51 118	80.57 120	84.36 106	89.42 123	68.69 115	89.97 74	91.50 110	74.46 114	75.04 239	90.41 130	53.82 233	94.54 104	77.56 113	82.91 201	89.86 214
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ETV-MVS		84.90 65	84.67 65	85.59 67	89.39 125	68.66 116	88.74 117	92.64 65	79.97 15	84.10 77	85.71 254	69.32 76	95.38 69	80.82 85	91.37 86	92.72 104

plane_prior3						68.60 117			78.44 31	78.92 141

CHOSEN 1792x2688		77.63 214	75.69 225	83.44 146	89.98 109	68.58 118	78.70 321	87.50 224	56.38 355	75.80 216	86.84 222	58.67 194	91.40 236	61.58 262	85.75 162	90.34 187

plane_prior7					90.08 103	68.51 119

fmvsm_l_conf0.5_n_a		84.13 69	84.16 71	84.06 125	85.38 239	68.40 120	88.34 132	86.85 237	67.48 250	87.48 34	93.40 61	70.89 58	91.61 222	88.38 25	89.22 115	92.16 129

ACMM	73.20 8	80.78 134	79.84 135	83.58 143	89.31 131	68.37 121	89.99 73	91.60 104	70.28 194	77.25 180	89.66 144	53.37 238	93.53 149	74.24 148	82.85 202	88.85 247
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs4		74.03 261	71.91 268	80.39 232	81.96 311	68.32 122	81.45 286	82.14 303	59.32 333	69.87 297	85.13 270	52.40 244	88.13 293	60.21 272	74.74 309	84.73 327

NP-MVS					89.62 115	68.32 122					90.24 132

test222					91.50 77	68.26 124	84.16 248	83.20 290	54.63 361	79.74 129	91.63 99	58.97 193			91.42 85	86.77 293

CDS-MVSNet		79.07 176	77.70 189	83.17 159	87.60 197	68.23 125	84.40 244	86.20 246	67.49 249	76.36 204	86.54 238	61.54 162	90.79 252	61.86 259	87.33 136	90.49 182
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PS-MVSNAJ		81.69 111	81.02 113	83.70 141	89.51 120	68.21 126	84.28 246	90.09 149	70.79 182	81.26 116	85.62 259	63.15 138	94.29 111	75.62 136	88.87 119	88.59 255

fmvsm_s_conf0.5_n_a		83.63 78	83.41 77	84.28 111	86.14 227	68.12 127	89.43 90	82.87 296	70.27 195	87.27 37	93.80 54	69.09 78	91.58 224	88.21 26	83.65 189	93.14 93

UGNet		80.83 128	79.59 140	84.54 98	88.04 178	68.09 128	89.42 91	88.16 206	76.95 59	76.22 207	89.46 153	49.30 286	93.94 127	68.48 204	90.31 98	91.60 140
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 86	82.99 85	84.28 111	83.79 272	68.07 129	89.34 95	82.85 297	69.80 205	87.36 36	94.06 42	68.34 88	91.56 226	87.95 27	83.46 195	93.21 90

UA-Net		85.08 62	84.96 62	85.45 70	92.07 70	68.07 129	89.78 80	90.86 126	82.48 3	84.60 68	93.20 66	69.35 75	95.22 74	71.39 174	90.88 92	93.07 95

xiu_mvs_v2_base		81.69 111	81.05 112	83.60 142	89.15 138	68.03 131	84.46 240	90.02 150	70.67 185	81.30 115	86.53 239	63.17 137	94.19 119	75.60 137	88.54 124	88.57 256

DELS-MVS		85.41 57	85.30 58	85.77 64	88.49 162	67.93 132	85.52 219	93.44 27	78.70 29	83.63 87	89.03 164	74.57 24	95.71 56	80.26 92	94.04 59	93.66 65
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
EI-MVSNet-Vis-set		84.19 68	83.81 73	85.31 73	88.18 172	67.85 133	87.66 155	89.73 159	80.05 14	82.95 92	89.59 148	70.74 61	94.82 95	80.66 89	84.72 169	93.28 86

PLC	70.83 11	78.05 201	76.37 220	83.08 163	91.88 74	67.80 134	88.19 137	89.46 165	64.33 287	69.87 297	88.38 183	53.66 234	93.58 144	58.86 284	82.73 204	87.86 266
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TAMVS		78.89 181	77.51 194	83.03 166	87.80 187	67.79 135	84.72 231	85.05 260	67.63 246	76.75 193	87.70 199	62.25 152	90.82 251	58.53 288	87.13 139	90.49 182

CLD-MVS		82.31 99	81.65 105	84.29 110	88.47 163	67.73 136	85.81 210	92.35 74	75.78 86	78.33 156	86.58 236	64.01 128	94.35 110	76.05 131	87.48 135	90.79 168
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
iter_conf_final		80.63 136	79.35 146	84.46 102	89.36 127	67.70 137	89.85 75	84.49 267	73.19 145	78.30 157	88.94 165	45.98 312	94.56 102	79.59 96	84.48 175	91.11 156

hse-mvs2		81.72 109	80.94 115	84.07 123	88.72 155	67.68 138	85.87 206	87.26 229	76.02 83	84.67 64	88.22 189	61.54 162	93.48 151	82.71 70	73.44 322	91.06 159

AUN-MVS		79.21 172	77.60 192	84.05 128	88.71 156	67.61 139	85.84 208	87.26 229	69.08 225	77.23 182	88.14 194	53.20 240	93.47 152	75.50 139	73.45 321	91.06 159

CS-MVS		86.69 35	86.95 31	85.90 63	90.76 91	67.57 140	92.83 17	93.30 32	79.67 17	84.57 69	92.27 86	71.47 53	95.02 86	84.24 54	93.46 63	95.13 6

EI-MVSNet-UG-set		83.81 72	83.38 78	85.09 80	87.87 183	67.53 141	87.44 161	89.66 160	79.74 16	82.23 101	89.41 157	70.24 66	94.74 98	79.95 93	83.92 182	92.99 100

Effi-MVS+		83.62 79	83.08 82	85.24 75	88.38 167	67.45 142	88.89 109	89.15 179	75.50 92	82.27 100	88.28 186	69.61 73	94.45 109	77.81 111	87.84 130	93.84 59

EG-PatchMatch MVS		74.04 259	71.82 269	80.71 227	84.92 250	67.42 143	85.86 207	88.08 209	66.04 267	64.22 347	83.85 289	35.10 365	92.56 189	57.44 297	80.83 226	82.16 354

OMC-MVS		82.69 95	81.97 102	84.85 89	88.75 154	67.42 143	87.98 144	90.87 125	74.92 103	79.72 130	91.65 97	62.19 154	93.96 124	75.26 140	86.42 150	93.16 92

PatchMatch-RL		72.38 277	70.90 280	76.80 291	88.60 159	67.38 145	79.53 309	76.17 353	62.75 306	69.36 302	82.00 320	45.51 318	84.89 320	53.62 318	80.58 230	78.12 368

LS3D		76.95 226	74.82 239	83.37 150	90.45 95	67.36 146	89.15 102	86.94 235	61.87 315	69.52 300	90.61 126	51.71 259	94.53 105	46.38 358	86.71 146	88.21 261

fmvsm_s_conf0.5_n		83.80 73	83.71 74	84.07 123	86.69 221	67.31 147	89.46 89	83.07 292	71.09 177	86.96 41	93.70 55	69.02 83	91.47 233	88.79 18	84.62 171	93.44 80

fmvsm_s_conf0.1_n		83.56 80	83.38 78	84.10 118	84.86 251	67.28 148	89.40 93	83.01 293	70.67 185	87.08 38	93.96 50	68.38 87	91.45 234	88.56 22	84.50 172	93.56 75

PS-MVSNAJss		82.07 103	81.31 107	84.34 108	86.51 223	67.27 149	89.27 96	91.51 107	71.75 161	79.37 134	90.22 134	63.15 138	94.27 113	77.69 112	82.36 209	91.49 146

114514_t		80.68 135	79.51 141	84.20 115	94.09 38	67.27 149	89.64 85	91.11 119	58.75 340	74.08 251	90.72 124	58.10 198	95.04 85	69.70 191	89.42 113	90.30 190

casdiffmvs_mvg		85.99 44	86.09 46	85.70 66	87.65 195	67.22 151	88.69 119	93.04 38	79.64 18	85.33 52	92.54 83	73.30 35	94.50 107	83.49 59	91.14 89	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
CS-MVS-test		86.29 42	86.48 37	85.71 65	91.02 83	67.21 152	92.36 29	93.78 18	78.97 28	83.51 88	91.20 111	70.65 63	95.15 77	81.96 76	94.89 41	94.77 22

anonymousdsp		78.60 187	77.15 200	82.98 169	80.51 332	67.08 153	87.24 167	89.53 163	65.66 272	75.16 234	87.19 216	52.52 241	92.25 202	77.17 118	79.34 246	89.61 222

MVS		78.19 197	76.99 204	81.78 197	85.66 233	66.99 154	84.66 232	90.47 135	55.08 360	72.02 274	85.27 265	63.83 130	94.11 122	66.10 224	89.80 109	84.24 331

HQP5-MVS						66.98 155

HQP-MVS		82.61 97	82.02 100	84.37 105	89.33 128	66.98 155	89.17 98	92.19 82	76.41 72	77.23 182	90.23 133	60.17 189	95.11 80	77.47 114	85.99 158	91.03 161

Fast-Effi-MVS+-dtu		78.02 202	76.49 216	82.62 184	83.16 288	66.96 157	86.94 174	87.45 226	72.45 152	71.49 279	84.17 285	54.79 223	91.58 224	67.61 210	80.31 234	89.30 230

F-COLMAP		76.38 236	74.33 246	82.50 186	89.28 133	66.95 158	88.41 127	89.03 183	64.05 291	66.83 325	88.61 176	46.78 304	92.89 181	57.48 296	78.55 252	87.67 269

mvsmamba		81.69 111	80.74 117	84.56 97	87.45 202	66.72 159	91.26 48	85.89 251	74.66 109	78.23 159	90.56 127	54.33 227	94.91 88	80.73 88	83.54 193	92.04 134

HyFIR lowres test		77.53 215	75.40 232	83.94 136	89.59 116	66.62 160	80.36 300	88.64 201	56.29 356	76.45 200	85.17 269	57.64 203	93.28 158	61.34 265	83.10 200	91.91 135

ACMH	67.68 16	75.89 241	73.93 249	81.77 198	88.71 156	66.61 161	88.62 122	89.01 185	69.81 204	66.78 326	86.70 230	41.95 341	91.51 231	55.64 310	78.14 259	87.17 282
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
jajsoiax		79.29 170	77.96 177	83.27 153	84.68 254	66.57 162	89.25 97	90.16 147	69.20 221	75.46 222	89.49 150	45.75 317	93.13 172	76.84 121	80.80 227	90.11 198

VDD-MVS		83.01 93	82.36 94	84.96 84	91.02 83	66.40 163	88.91 108	88.11 207	77.57 41	84.39 72	93.29 64	52.19 247	93.91 131	77.05 119	88.70 122	94.57 29

mvs_tets		79.13 174	77.77 186	83.22 157	84.70 253	66.37 164	89.17 98	90.19 146	69.38 214	75.40 225	89.46 153	44.17 325	93.15 170	76.78 124	80.70 229	90.14 195

PAPM_NR		83.02 92	82.41 92	84.82 90	92.47 67	66.37 164	87.93 148	91.80 98	73.82 127	77.32 179	90.66 125	67.90 91	94.90 91	70.37 183	89.48 112	93.19 91

EC-MVSNet		86.01 43	86.38 38	84.91 88	89.31 131	66.27 166	92.32 30	93.63 21	79.37 20	84.17 76	91.88 93	69.04 82	95.43 65	83.93 57	93.77 61	93.01 99

pmmvs-eth3d		70.50 295	67.83 308	78.52 267	77.37 357	66.18 167	81.82 279	81.51 309	58.90 338	63.90 350	80.42 332	42.69 333	86.28 307	58.56 287	65.30 359	83.11 344

IB-MVS	68.01 15	75.85 242	73.36 256	83.31 151	84.76 252	66.03 168	83.38 261	85.06 259	70.21 197	69.40 301	81.05 324	45.76 316	94.66 101	65.10 233	75.49 293	89.25 231
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		73.83 262	72.67 261	77.30 286	83.87 271	66.02 169	81.82 279	84.66 264	61.37 319	68.61 309	82.82 308	47.29 299	88.21 291	59.27 278	84.32 178	77.68 369

FE-MVS		77.78 208	75.68 226	84.08 122	88.09 176	66.00 170	83.13 266	87.79 218	68.42 240	78.01 166	85.23 267	45.50 319	95.12 78	59.11 281	85.83 161	91.11 156

test_0402		72.79 275	70.44 285	79.84 244	88.13 173	65.99 171	85.93 204	84.29 271	65.57 273	67.40 320	85.49 261	46.92 303	92.61 187	35.88 381	74.38 312	80.94 360

BH-RMVSNet		79.61 158	78.44 167	83.14 160	89.38 126	65.93 172	84.95 227	87.15 232	73.56 134	78.19 161	89.79 141	56.67 212	93.36 156	59.53 277	86.74 145	90.13 196

BH-untuned		79.47 163	78.60 163	82.05 192	89.19 137	65.91 173	86.07 201	88.52 203	72.18 157	75.42 224	87.69 200	61.15 173	93.54 148	60.38 270	86.83 144	86.70 295

cascas		76.72 229	74.64 240	82.99 168	85.78 232	65.88 174	82.33 275	89.21 176	60.85 321	72.74 264	81.02 325	47.28 300	93.75 140	67.48 212	85.02 165	89.34 228

patch_mono-2		83.65 76	84.54 66	80.99 220	90.06 107	65.83 175	84.21 247	88.74 198	71.60 167	85.01 55	92.44 84	74.51 25	83.50 329	82.15 75	92.15 75	93.64 71

iter_conf05		80.00 154	78.70 160	83.91 137	87.84 185	65.83 175	88.84 112	84.92 262	71.61 166	78.70 144	88.94 165	43.88 327	94.56 102	79.28 97	84.28 179	91.33 149

MSDG		73.36 268	70.99 279	80.49 231	84.51 259	65.80 177	80.71 294	86.13 248	65.70 271	65.46 338	83.74 293	44.60 322	90.91 250	51.13 331	76.89 270	84.74 326

旧先验1					91.96 71	65.79 178		86.37 244			93.08 71	69.31 77			92.74 68	88.74 252

casdiffmvs		85.11 61	85.14 60	85.01 82	87.20 211	65.77 179	87.75 153	92.83 55	77.84 37	84.36 73	92.38 85	72.15 44	93.93 130	81.27 81	90.48 96	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
COLMAP_ROB	66.92 17	73.01 272	70.41 286	80.81 225	87.13 213	65.63 180	88.30 134	84.19 274	62.96 301	63.80 351	87.69 200	38.04 357	92.56 189	46.66 355	74.91 307	84.24 331
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
EIA-MVS		83.31 87	82.80 89	84.82 90	89.59 116	65.59 181	88.21 136	92.68 60	74.66 109	78.96 139	86.42 241	69.06 80	95.26 73	75.54 138	90.09 103	93.62 72

v7n		78.97 179	77.58 193	83.14 160	83.45 279	65.51 182	88.32 133	91.21 114	73.69 130	72.41 269	86.32 244	57.93 199	93.81 135	69.18 196	75.65 290	90.11 198

V42		79.38 169	78.24 173	82.83 174	81.10 326	65.50 183	85.55 215	89.82 155	71.57 168	78.21 160	86.12 248	60.66 181	93.18 169	75.64 135	75.46 296	89.81 217

bld_raw_dy_0_64		77.29 221	75.98 223	81.22 213	85.04 248	65.47 184	88.14 142	77.56 342	69.20 221	73.77 253	89.40 159	42.24 338	88.85 284	76.78 124	81.64 217	89.33 229

RRT_MVS		80.35 146	79.22 151	83.74 140	87.63 196	65.46 185	91.08 54	88.92 191	73.82 127	76.44 203	90.03 136	49.05 291	94.25 117	76.84 121	79.20 249	91.51 143

PVSNet_BlendedMVS		80.60 138	80.02 130	82.36 189	88.85 146	65.40 186	86.16 199	92.00 87	69.34 215	78.11 163	86.09 249	66.02 112	94.27 113	71.52 171	82.06 212	87.39 276

PVSNet_Blended		80.98 124	80.34 125	82.90 172	88.85 146	65.40 186	84.43 242	92.00 87	67.62 247	78.11 163	85.05 273	66.02 112	94.27 113	71.52 171	89.50 111	89.01 239

baseline		84.93 63	84.98 61	84.80 92	87.30 209	65.39 188	87.30 165	92.88 52	77.62 39	84.04 79	92.26 87	71.81 47	93.96 124	81.31 80	90.30 99	95.03 8

test_djsdf		80.30 147	79.32 147	83.27 153	83.98 269	65.37 189	90.50 62	90.38 137	68.55 236	76.19 208	88.70 172	56.44 213	93.46 153	78.98 99	80.14 237	90.97 164

ACMH+	68.96 14	76.01 240	74.01 248	82.03 193	88.60 159	65.31 190	88.86 110	87.55 222	70.25 196	67.75 314	87.47 208	41.27 342	93.19 168	58.37 289	75.94 287	87.60 271

CR-MVSNet		73.37 266	71.27 276	79.67 249	81.32 324	65.19 191	75.92 340	80.30 322	59.92 328	72.73 265	81.19 322	52.50 242	86.69 303	59.84 274	77.71 261	87.11 286

RPMNet		73.51 265	70.49 284	82.58 185	81.32 324	65.19 191	75.92 340	92.27 76	57.60 348	72.73 265	76.45 361	52.30 245	95.43 65	48.14 350	77.71 261	87.11 286

BH-w/o		78.21 195	77.33 198	80.84 224	88.81 150	65.13 193	84.87 228	87.85 217	69.75 208	74.52 247	84.74 277	61.34 168	93.11 173	58.24 291	85.84 160	84.27 330

thisisatest0530		79.40 167	77.76 187	84.31 109	87.69 194	65.10 194	87.36 162	84.26 273	70.04 198	77.42 176	88.26 188	49.94 277	94.79 97	70.20 184	84.70 170	93.03 97

FA-MVS(test-final)		80.96 125	79.91 133	84.10 118	88.30 170	65.01 195	84.55 237	90.01 151	73.25 143	79.61 131	87.57 203	58.35 197	94.72 99	71.29 175	86.25 153	92.56 111

v10		79.74 157	78.67 161	82.97 170	84.06 267	64.95 196	87.88 151	90.62 130	73.11 146	75.11 236	86.56 237	61.46 165	94.05 123	73.68 151	75.55 292	89.90 212

SDMVSNet		80.38 143	80.18 129	80.99 220	89.03 144	64.94 197	80.45 299	89.40 166	75.19 98	76.61 198	89.98 137	60.61 183	87.69 298	76.83 123	83.55 191	90.33 188

dcpmvs_2		85.63 52	86.15 44	84.06 125	91.71 75	64.94 197	86.47 190	91.87 95	73.63 131	86.60 43	93.02 72	76.57 15	91.87 216	83.36 60	92.15 75	95.35 3

IterMVS-SCA-FT		75.43 248	73.87 251	80.11 239	82.69 300	64.85 199	81.57 284	83.47 284	69.16 223	70.49 285	84.15 286	51.95 254	88.15 292	69.23 195	72.14 331	87.34 278

MVSTER		79.01 177	77.88 181	82.38 188	83.07 289	64.80 200	84.08 251	88.95 189	69.01 229	78.69 145	87.17 217	54.70 224	92.43 193	74.69 142	80.57 231	89.89 213

Anonymous20240529		80.19 150	78.89 158	84.10 118	90.60 92	64.75 201	88.95 107	90.90 123	65.97 269	80.59 122	91.17 113	49.97 276	93.73 142	69.16 197	82.70 206	93.81 60

XVG-ACMP-BASELINE		76.11 239	74.27 247	81.62 200	83.20 285	64.67 202	83.60 258	89.75 158	69.75 208	71.85 275	87.09 219	32.78 368	92.11 206	69.99 188	80.43 233	88.09 262

v1192		79.59 160	78.43 168	83.07 164	83.55 277	64.52 203	86.93 175	90.58 131	70.83 181	77.78 170	85.90 250	59.15 192	93.94 127	73.96 150	77.19 267	90.76 170

Fast-Effi-MVS+		80.81 129	79.92 132	83.47 145	88.85 146	64.51 204	85.53 217	89.39 167	70.79 182	78.49 152	85.06 272	67.54 94	93.58 144	67.03 219	86.58 147	92.32 120

v1144		80.03 152	79.03 155	83.01 167	83.78 273	64.51 204	87.11 170	90.57 133	71.96 160	78.08 165	86.20 246	61.41 166	93.94 127	74.93 141	77.23 265	90.60 177

v8		79.97 155	79.02 156	82.80 177	84.09 266	64.50 206	87.96 145	90.29 144	74.13 122	75.24 233	86.81 223	62.88 143	93.89 133	74.39 146	75.40 299	90.00 206

EPP-MVSNet		83.40 84	83.02 84	84.57 96	90.13 101	64.47 207	92.32 30	90.73 128	74.45 115	79.35 135	91.10 114	69.05 81	95.12 78	72.78 163	87.22 138	94.13 44

GeoE		81.71 110	81.01 114	83.80 139	89.51 120	64.45 208	88.97 106	88.73 199	71.27 173	78.63 148	89.76 142	66.32 107	93.20 166	69.89 189	86.02 157	93.74 63

UniMVSNet (Re)		81.60 115	81.11 111	83.09 162	88.38 167	64.41 209	87.60 156	93.02 42	78.42 32	78.56 150	88.16 190	69.78 71	93.26 159	69.58 193	76.49 276	91.60 140

LTVRE_ROB	69.57 13	76.25 237	74.54 243	81.41 206	88.60 159	64.38 210	79.24 313	89.12 182	70.76 184	69.79 299	87.86 197	49.09 289	93.20 166	56.21 309	80.16 235	86.65 296
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		78.97 179	77.69 190	82.81 176	90.54 94	64.29 211	90.11 72	91.51 107	65.01 279	76.16 212	88.13 195	50.56 270	93.03 179	69.68 192	77.56 264	91.11 156

testdata				79.97 241	90.90 86	64.21 212		84.71 263	59.27 334	85.40 51	92.91 73	62.02 157	89.08 277	68.95 199	91.37 86	86.63 297

v2v482		80.23 148	79.29 148	83.05 165	83.62 275	64.14 213	87.04 171	89.97 152	73.61 132	78.18 162	87.22 214	61.10 174	93.82 134	76.11 129	76.78 274	91.18 154

VDDNet		81.52 116	80.67 119	84.05 128	90.44 96	64.13 214	89.73 82	85.91 250	71.11 176	83.18 90	93.48 58	50.54 271	93.49 150	73.40 156	88.25 128	94.54 30

PAPR		81.66 114	80.89 116	83.99 133	90.27 98	64.00 215	86.76 183	91.77 101	68.84 232	77.13 188	89.50 149	67.63 93	94.88 93	67.55 211	88.52 125	93.09 94

v144192		79.47 163	78.37 169	82.78 180	83.35 280	63.96 216	86.96 173	90.36 140	69.99 200	77.50 174	85.67 257	60.66 181	93.77 138	74.27 147	76.58 275	90.62 175

v1921920		79.22 171	78.03 176	82.80 177	83.30 282	63.94 217	86.80 179	90.33 141	69.91 203	77.48 175	85.53 260	58.44 196	93.75 140	73.60 152	76.85 272	90.71 173

tttt0517		79.40 167	77.91 179	83.90 138	88.10 175	63.84 218	88.37 131	84.05 275	71.45 170	76.78 192	89.12 161	49.93 279	94.89 92	70.18 185	83.18 199	92.96 101

thisisatest0515		77.33 219	75.38 233	83.18 158	85.27 241	63.80 219	82.11 278	83.27 287	65.06 277	75.91 213	83.84 290	49.54 281	94.27 113	67.24 215	86.19 154	91.48 147

diffmvs		82.10 101	81.88 103	82.76 182	83.00 292	63.78 220	83.68 254	89.76 157	72.94 150	82.02 103	89.85 140	65.96 114	90.79 252	82.38 74	87.30 137	93.71 64
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_yl		81.17 121	80.47 123	83.24 155	89.13 139	63.62 221	86.21 197	89.95 153	72.43 155	81.78 108	89.61 146	57.50 205	93.58 144	70.75 178	86.90 142	92.52 112

DCV-MVSNet		81.17 121	80.47 123	83.24 155	89.13 139	63.62 221	86.21 197	89.95 153	72.43 155	81.78 108	89.61 146	57.50 205	93.58 144	70.75 178	86.90 142	92.52 112

AllTest		70.96 288	68.09 303	79.58 251	85.15 244	63.62 221	84.58 236	79.83 326	62.31 310	60.32 362	86.73 224	32.02 369	88.96 281	50.28 336	71.57 335	86.15 303

TestCases				79.58 251	85.15 244	63.62 221		79.83 326	62.31 310	60.32 362	86.73 224	32.02 369	88.96 281	50.28 336	71.57 335	86.15 303

v1240		78.99 178	77.78 185	82.64 183	83.21 284	63.54 225	86.62 186	90.30 143	69.74 210	77.33 178	85.68 256	57.04 210	93.76 139	73.13 160	76.92 269	90.62 175

CHOSEN 280x420		66.51 325	64.71 326	71.90 330	81.45 319	63.52 226	57.98 389	68.95 377	53.57 362	62.59 356	76.70 359	46.22 310	75.29 376	55.25 311	79.68 240	76.88 371

IterMVS		74.29 255	72.94 260	78.35 269	81.53 318	63.49 227	81.58 283	82.49 300	68.06 244	69.99 294	83.69 294	51.66 260	85.54 313	65.85 227	71.64 334	86.01 307
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet_NR-MVSNet		81.88 106	81.54 106	82.92 171	88.46 164	63.46 228	87.13 168	92.37 73	80.19 12	78.38 154	89.14 160	71.66 52	93.05 176	70.05 186	76.46 277	92.25 123

DU-MVS		81.12 123	80.52 122	82.90 172	87.80 187	63.46 228	87.02 172	91.87 95	79.01 26	78.38 154	89.07 162	65.02 121	93.05 176	70.05 186	76.46 277	92.20 126

LFMVS		81.82 108	81.23 109	83.57 144	91.89 73	63.43 230	89.84 76	81.85 307	77.04 58	83.21 89	93.10 67	52.26 246	93.43 155	71.98 169	89.95 107	93.85 57

NR-MVSNet		80.23 148	79.38 144	82.78 180	87.80 187	63.34 231	86.31 194	91.09 120	79.01 26	72.17 272	89.07 162	67.20 98	92.81 185	66.08 225	75.65 290	92.20 126

IS-MVSNet		83.15 88	82.81 88	84.18 116	89.94 110	63.30 232	91.59 43	88.46 204	79.04 25	79.49 133	92.16 88	65.10 120	94.28 112	67.71 209	91.86 81	94.95 10

TR-MVS		77.44 216	76.18 221	81.20 214	88.24 171	63.24 233	84.61 235	86.40 243	67.55 248	77.81 169	86.48 240	54.10 230	93.15 170	57.75 295	82.72 205	87.20 281

MVS_Test		83.15 88	83.06 83	83.41 149	86.86 215	63.21 234	86.11 200	92.00 87	74.31 116	82.87 94	89.44 156	70.03 67	93.21 163	77.39 116	88.50 126	93.81 60

IterMVS-LS		80.06 151	79.38 144	82.11 191	85.89 230	63.20 235	86.79 180	89.34 168	74.19 119	75.45 223	86.72 226	66.62 101	92.39 195	72.58 165	76.86 271	90.75 171
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		80.52 141	79.98 131	82.12 190	84.28 261	63.19 236	86.41 191	88.95 189	74.18 120	78.69 145	87.54 206	66.62 101	92.43 193	72.57 166	80.57 231	90.74 172

CANet_DTU		80.61 137	79.87 134	82.83 174	85.60 235	63.17 237	87.36 162	88.65 200	76.37 76	75.88 214	88.44 182	53.51 236	93.07 175	73.30 157	89.74 110	92.25 123

GBi-Net		78.40 190	77.40 195	81.40 207	87.60 197	63.01 238	88.39 128	89.28 170	71.63 163	75.34 227	87.28 210	54.80 220	91.11 242	62.72 247	79.57 241	90.09 200

test1		78.40 190	77.40 195	81.40 207	87.60 197	63.01 238	88.39 128	89.28 170	71.63 163	75.34 227	87.28 210	54.80 220	91.11 242	62.72 247	79.57 241	90.09 200

FMVSNet1		77.44 216	76.12 222	81.40 207	86.81 218	63.01 238	88.39 128	89.28 170	70.49 190	74.39 248	87.28 210	49.06 290	91.11 242	60.91 267	78.52 253	90.09 200

TAPA-MVS	73.13 9	79.15 173	77.94 178	82.79 179	89.59 116	62.99 241	88.16 139	91.51 107	65.77 270	77.14 187	91.09 115	60.91 177	93.21 163	50.26 338	87.05 140	92.17 128
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FMVSNet2		78.20 196	77.21 199	81.20 214	87.60 197	62.89 242	87.47 160	89.02 184	71.63 163	75.29 232	87.28 210	54.80 220	91.10 245	62.38 252	79.38 245	89.61 222

GA-MVS		76.87 227	75.17 237	81.97 195	82.75 298	62.58 243	81.44 287	86.35 245	72.16 159	74.74 243	82.89 306	46.20 311	92.02 209	68.85 201	81.09 223	91.30 152

D2MVS		74.82 252	73.21 257	79.64 250	79.81 341	62.56 244	80.34 301	87.35 227	64.37 286	68.86 306	82.66 310	46.37 307	90.10 261	67.91 208	81.24 221	86.25 300

FMVSNet3		77.88 206	76.85 207	80.97 222	86.84 217	62.36 245	86.52 189	88.77 194	71.13 175	75.34 227	86.66 232	54.07 231	91.10 245	62.72 247	79.57 241	89.45 226

TranMVSNet+NR-MVSNet		80.84 127	80.31 126	82.42 187	87.85 184	62.33 246	87.74 154	91.33 112	80.55 9	77.99 167	89.86 139	65.23 119	92.62 186	67.05 218	75.24 304	92.30 121

1314		76.53 230	75.30 236	80.21 237	83.93 270	62.32 247	84.66 232	88.81 192	60.23 325	70.16 291	84.07 287	55.30 217	90.73 254	67.37 213	83.21 198	87.59 273

MG-MVS		83.41 83	83.45 76	83.28 152	92.74 62	62.28 248	88.17 138	89.50 164	75.22 96	81.49 111	92.74 82	66.75 100	95.11 80	72.85 162	91.58 83	92.45 117

SCA		74.22 257	72.33 266	79.91 242	84.05 268	62.17 249	79.96 306	79.29 332	66.30 264	72.38 270	80.13 334	51.95 254	88.60 287	59.25 279	77.67 263	88.96 243

PMMVS		69.34 304	68.67 296	71.35 336	75.67 363	62.03 250	75.17 346	73.46 363	50.00 372	68.68 307	79.05 343	52.07 252	78.13 354	61.16 266	82.77 203	73.90 375

eth_miper_zixun_eth		77.92 205	76.69 213	81.61 202	83.00 292	61.98 251	83.15 265	89.20 177	69.52 212	74.86 242	84.35 283	61.76 158	92.56 189	71.50 173	72.89 326	90.28 191

v148		78.72 184	77.80 184	81.47 204	82.73 299	61.96 252	86.30 195	88.08 209	73.26 142	76.18 209	85.47 262	62.46 148	92.36 197	71.92 170	73.82 318	90.09 200

PAPM		77.68 213	76.40 219	81.51 203	87.29 210	61.85 253	83.78 253	89.59 162	64.74 281	71.23 280	88.70 172	62.59 145	93.66 143	52.66 323	87.03 141	89.01 239

cl22		78.07 200	77.01 202	81.23 212	82.37 308	61.83 254	83.55 259	87.98 211	68.96 230	75.06 238	83.87 288	61.40 167	91.88 215	73.53 153	76.39 279	89.98 209

baseline2		75.70 243	73.83 252	81.30 210	83.26 283	61.79 255	82.57 274	80.65 316	66.81 252	66.88 324	83.42 298	57.86 201	92.19 204	63.47 241	79.57 241	89.91 211

JIA-IIPM		66.32 327	62.82 338	76.82 290	77.09 358	61.72 256	65.34 382	75.38 354	58.04 345	64.51 345	62.32 383	42.05 340	86.51 305	51.45 329	69.22 345	82.21 352

miper_ehance_all_eth		78.59 188	77.76 187	81.08 218	82.66 301	61.56 257	83.65 255	89.15 179	68.87 231	75.55 219	83.79 292	66.49 104	92.03 208	73.25 158	76.39 279	89.64 221

c3_l		78.75 182	77.91 179	81.26 211	82.89 296	61.56 257	84.09 250	89.13 181	69.97 201	75.56 218	84.29 284	66.36 106	92.09 207	73.47 155	75.48 294	90.12 197

miper_enhance_ethall		77.87 207	76.86 206	80.92 223	81.65 315	61.38 259	82.68 272	88.98 186	65.52 274	75.47 220	82.30 314	65.76 116	92.00 210	72.95 161	76.39 279	89.39 227

ppachtmachnet_test		70.04 299	67.34 316	78.14 272	79.80 342	61.13 260	79.19 315	80.59 317	59.16 335	65.27 340	79.29 342	46.75 305	87.29 300	49.33 342	66.72 352	86.00 309

TDRefinement		67.49 317	64.34 327	76.92 289	73.47 375	61.07 261	84.86 229	82.98 294	59.77 329	58.30 369	85.13 270	26.06 379	87.89 295	47.92 352	60.59 370	81.81 356

VNet		82.21 100	82.41 92	81.62 200	90.82 88	60.93 262	84.47 238	89.78 156	76.36 77	84.07 78	91.88 93	64.71 124	90.26 258	70.68 180	88.89 118	93.66 65

ab-mvs		79.51 161	78.97 157	81.14 216	88.46 164	60.91 263	83.84 252	89.24 175	70.36 191	79.03 138	88.87 169	63.23 136	90.21 260	65.12 232	82.57 207	92.28 122

PatchmatchNet		73.12 271	71.33 275	78.49 268	83.18 286	60.85 264	79.63 308	78.57 336	64.13 288	71.73 276	79.81 339	51.20 263	85.97 310	57.40 298	76.36 284	88.66 253
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VPA-MVSNet		80.60 138	80.55 121	80.76 226	88.07 177	60.80 265	86.86 177	91.58 105	75.67 90	80.24 125	89.45 155	63.34 132	90.25 259	70.51 182	79.22 248	91.23 153

EGC-MVSNET		52.07 354	47.05 358	67.14 355	83.51 278	60.71 266	80.50 298	67.75 378	0.07 402	0.43 403	75.85 366	24.26 382	81.54 340	28.82 387	62.25 364	59.16 387

Anonymous202405211		78.25 193	77.01 202	81.99 194	91.03 82	60.67 267	84.77 230	83.90 277	70.65 188	80.00 128	91.20 111	41.08 344	91.43 235	65.21 231	85.26 164	93.85 57

ITE_SJBPF				78.22 270	81.77 314	60.57 268		83.30 286	69.25 218	67.54 316	87.20 215	36.33 362	87.28 301	54.34 315	74.62 310	86.80 292

MDA-MVSNet-bldmvs		66.68 323	63.66 332	75.75 297	79.28 349	60.56 269	73.92 354	78.35 337	64.43 284	50.13 383	79.87 338	44.02 326	83.67 327	46.10 360	56.86 373	83.03 346

cl____		77.72 210	76.76 210	80.58 229	82.49 305	60.48 270	83.09 267	87.87 215	69.22 219	74.38 249	85.22 268	62.10 155	91.53 229	71.09 176	75.41 298	89.73 220

DIV-MVS_self_test		77.72 210	76.76 210	80.58 229	82.48 306	60.48 270	83.09 267	87.86 216	69.22 219	74.38 249	85.24 266	62.10 155	91.53 229	71.09 176	75.40 299	89.74 219

1112_ss		77.40 218	76.43 218	80.32 235	89.11 143	60.41 272	83.65 255	87.72 220	62.13 313	73.05 262	86.72 226	62.58 146	89.97 262	62.11 257	80.80 227	90.59 178

tt0805		78.73 183	77.83 182	81.43 205	85.17 242	60.30 273	89.41 92	90.90 123	71.21 174	77.17 186	88.73 171	46.38 306	93.21 163	72.57 166	78.96 250	90.79 168

UniMVSNet_ETH3D		79.10 175	78.24 173	81.70 199	86.85 216	60.24 274	87.28 166	88.79 193	74.25 118	76.84 189	90.53 129	49.48 282	91.56 226	67.98 207	82.15 210	93.29 85

HY-MVS	69.67 12	77.95 204	77.15 200	80.36 233	87.57 201	60.21 275	83.37 262	87.78 219	66.11 265	75.37 226	87.06 221	63.27 134	90.48 257	61.38 264	82.43 208	90.40 186

sd_testset		77.70 212	77.40 195	78.60 264	89.03 144	60.02 276	79.00 317	85.83 252	75.19 98	76.61 198	89.98 137	54.81 219	85.46 315	62.63 251	83.55 191	90.33 188

RPSCF		73.23 270	71.46 272	78.54 266	82.50 304	59.85 277	82.18 277	82.84 298	58.96 337	71.15 282	89.41 157	45.48 320	84.77 321	58.82 285	71.83 333	91.02 163

test_cas_vis1_n_1920		73.76 263	73.74 253	73.81 317	75.90 361	59.77 278	80.51 297	82.40 301	58.30 342	81.62 110	85.69 255	44.35 324	76.41 366	76.29 127	78.61 251	85.23 318

dmvs_re		71.14 286	70.58 282	72.80 325	81.96 311	59.68 279	75.60 344	79.34 331	68.55 236	69.27 304	80.72 330	49.42 283	76.54 363	52.56 324	77.79 260	82.19 353

miper_lstm_enhance		74.11 258	73.11 259	77.13 288	80.11 336	59.62 280	72.23 358	86.92 236	66.76 254	70.40 286	82.92 305	56.93 211	82.92 333	69.06 198	72.63 327	88.87 246

OurMVSNet-221017-0		74.26 256	72.42 265	79.80 245	83.76 274	59.59 281	85.92 205	86.64 239	66.39 263	66.96 323	87.58 202	39.46 349	91.60 223	65.76 228	69.27 344	88.22 260

Patchmatch-RL test		70.24 297	67.78 310	77.61 281	77.43 356	59.57 282	71.16 361	70.33 370	62.94 302	68.65 308	72.77 373	50.62 269	85.49 314	69.58 193	66.58 354	87.77 268

OpenMVS_ROB	64.09 19	70.56 294	68.19 300	77.65 280	80.26 333	59.41 283	85.01 225	82.96 295	58.76 339	65.43 339	82.33 313	37.63 359	91.23 241	45.34 365	76.03 286	82.32 351

our_test_3		69.14 305	67.00 318	75.57 300	79.80 342	58.80 284	77.96 329	77.81 339	59.55 331	62.90 355	78.25 352	47.43 298	83.97 325	51.71 327	67.58 351	83.93 336

ADS-MVSNet2		66.20 330	63.33 333	74.82 308	79.92 338	58.75 285	67.55 375	75.19 355	53.37 363	65.25 341	75.86 364	42.32 335	80.53 346	41.57 372	68.91 346	85.18 319

pm-mvs1		77.25 222	76.68 214	78.93 259	84.22 263	58.62 286	86.41 191	88.36 205	71.37 171	73.31 258	88.01 196	61.22 172	89.15 276	64.24 238	73.01 325	89.03 238

WR-MVS		79.49 162	79.22 151	80.27 236	88.79 152	58.35 287	85.06 224	88.61 202	78.56 30	77.65 172	88.34 184	63.81 131	90.66 255	64.98 234	77.22 266	91.80 138

FIs		82.07 103	82.42 91	81.04 219	88.80 151	58.34 288	88.26 135	93.49 26	76.93 60	78.47 153	91.04 117	69.92 70	92.34 199	69.87 190	84.97 166	92.44 118

CostFormer		75.24 251	73.90 250	79.27 255	82.65 302	58.27 289	80.80 291	82.73 299	61.57 316	75.33 230	83.13 302	55.52 215	91.07 248	64.98 234	78.34 258	88.45 257

Test_1112_low_res		76.40 235	75.44 230	79.27 255	89.28 133	58.09 290	81.69 282	87.07 233	59.53 332	72.48 268	86.67 231	61.30 169	89.33 272	60.81 269	80.15 236	90.41 185

tfpnnormal		74.39 254	73.16 258	78.08 273	86.10 229	58.05 291	84.65 234	87.53 223	70.32 193	71.22 281	85.63 258	54.97 218	89.86 263	43.03 369	75.02 306	86.32 299

test-LLR		72.94 274	72.43 264	74.48 311	81.35 322	58.04 292	78.38 324	77.46 343	66.66 256	69.95 295	79.00 345	48.06 296	79.24 349	66.13 222	84.83 167	86.15 303

test-mter		71.41 284	70.39 287	74.48 311	81.35 322	58.04 292	78.38 324	77.46 343	60.32 324	69.95 295	79.00 345	36.08 363	79.24 349	66.13 222	84.83 167	86.15 303

mvs_anonymous		79.42 166	79.11 154	80.34 234	84.45 260	57.97 294	82.59 273	87.62 221	67.40 251	76.17 211	88.56 179	68.47 86	89.59 268	70.65 181	86.05 156	93.47 79

tpm cat1		70.57 293	68.31 299	77.35 285	82.41 307	57.95 295	78.08 328	80.22 324	52.04 366	68.54 310	77.66 356	52.00 253	87.84 296	51.77 326	72.07 332	86.25 300

SixPastTwentyTwo		73.37 266	71.26 277	79.70 247	85.08 247	57.89 296	85.57 211	83.56 282	71.03 179	65.66 337	85.88 251	42.10 339	92.57 188	59.11 281	63.34 363	88.65 254

thres200		75.55 245	74.47 244	78.82 260	87.78 190	57.85 297	83.07 269	83.51 283	72.44 154	75.84 215	84.42 279	52.08 251	91.75 219	47.41 353	83.64 190	86.86 291

XXY-MVS		75.41 249	75.56 228	74.96 306	83.59 276	57.82 298	80.59 296	83.87 278	66.54 262	74.93 241	88.31 185	63.24 135	80.09 347	62.16 255	76.85 272	86.97 289

K. test v3		71.19 285	68.51 297	79.21 257	83.04 291	57.78 299	84.35 245	76.91 349	72.90 151	62.99 354	82.86 307	39.27 350	91.09 247	61.65 261	52.66 381	88.75 251

tfpn200view9		76.42 234	75.37 234	79.55 253	89.13 139	57.65 300	85.17 220	83.60 280	73.41 139	76.45 200	86.39 242	52.12 248	91.95 211	48.33 346	83.75 185	89.07 232

thres400		76.50 231	75.37 234	79.86 243	89.13 139	57.65 300	85.17 220	83.60 280	73.41 139	76.45 200	86.39 242	52.12 248	91.95 211	48.33 346	83.75 185	90.00 206

CMPMVS	51.72 21	70.19 298	68.16 301	76.28 293	73.15 377	57.55 302	79.47 310	83.92 276	48.02 374	56.48 375	84.81 275	43.13 330	86.42 306	62.67 250	81.81 216	84.89 324
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs6		74.69 253	73.39 255	78.61 263	81.38 321	57.48 303	86.64 185	87.95 213	64.99 280	70.18 289	86.61 233	50.43 272	89.52 269	62.12 256	70.18 341	88.83 248

test_vis1_n_1920		75.52 246	75.78 224	74.75 310	79.84 340	57.44 304	83.26 263	85.52 255	62.83 304	79.34 136	86.17 247	45.10 321	79.71 348	78.75 101	81.21 222	87.10 288

PVSNet_0	57.27 20	61.67 341	59.27 344	68.85 349	79.61 345	57.44 304	68.01 374	73.44 364	55.93 357	58.54 368	70.41 378	44.58 323	77.55 358	47.01 354	35.91 390	71.55 378

thres600view7		76.50 231	75.44 230	79.68 248	89.40 124	57.16 306	85.53 217	83.23 288	73.79 129	76.26 206	87.09 219	51.89 256	91.89 214	48.05 351	83.72 188	90.00 206

lessismore_v0				78.97 258	81.01 327	57.15 307		65.99 381		61.16 359	82.82 308	39.12 351	91.34 238	59.67 275	46.92 387	88.43 258

TransMVSNet (Re)		75.39 250	74.56 242	77.86 275	85.50 237	57.10 308	86.78 181	86.09 249	72.17 158	71.53 278	87.34 209	63.01 142	89.31 273	56.84 304	61.83 365	87.17 282

thres100view900		76.50 231	75.55 229	79.33 254	89.52 119	56.99 309	85.83 209	83.23 288	73.94 124	76.32 205	87.12 218	51.89 256	91.95 211	48.33 346	83.75 185	89.07 232

TESTMET0.1,1		69.89 301	69.00 295	72.55 327	79.27 350	56.85 310	78.38 324	74.71 360	57.64 347	68.09 312	77.19 358	37.75 358	76.70 362	63.92 239	84.09 181	84.10 334

WTY-MVS		75.65 244	75.68 226	75.57 300	86.40 224	56.82 311	77.92 331	82.40 301	65.10 276	76.18 209	87.72 198	63.13 141	80.90 344	60.31 271	81.96 213	89.00 241

MDA-MVSNet_test_wron		65.03 331	62.92 335	71.37 334	75.93 360	56.73 312	69.09 373	74.73 359	57.28 351	54.03 379	77.89 353	45.88 313	74.39 379	49.89 340	61.55 366	82.99 347

pmmvs3		57.79 344	54.26 349	68.37 352	64.02 390	56.72 313	75.12 349	65.17 383	40.20 382	52.93 380	69.86 379	20.36 386	75.48 373	45.45 364	55.25 379	72.90 377

tpm2		73.26 269	71.46 272	78.63 262	83.34 281	56.71 314	80.65 295	80.40 321	56.63 354	73.55 256	82.02 319	51.80 258	91.24 240	56.35 308	78.42 256	87.95 263

TinyColmap		67.30 320	64.81 325	74.76 309	81.92 313	56.68 315	80.29 302	81.49 310	60.33 323	56.27 376	83.22 299	24.77 381	87.66 299	45.52 363	69.47 343	79.95 364

YYNet1		65.03 331	62.91 336	71.38 333	75.85 362	56.60 316	69.12 372	74.66 361	57.28 351	54.12 378	77.87 354	45.85 314	74.48 378	49.95 339	61.52 367	83.05 345

PM-MVS		66.41 326	64.14 328	73.20 322	73.92 370	56.45 317	78.97 318	64.96 385	63.88 295	64.72 344	80.24 333	19.84 387	83.44 330	66.24 221	64.52 361	79.71 365

PVSNet	64.34 18	72.08 281	70.87 281	75.69 298	86.21 226	56.44 318	74.37 352	80.73 315	62.06 314	70.17 290	82.23 316	42.86 332	83.31 331	54.77 313	84.45 176	87.32 279

pmmvs5		71.55 283	70.20 289	75.61 299	77.83 354	56.39 319	81.74 281	80.89 312	57.76 346	67.46 318	84.49 278	49.26 287	85.32 317	57.08 301	75.29 302	85.11 322

WR-MVS_H		78.51 189	78.49 165	78.56 265	88.02 179	56.38 320	88.43 126	92.67 61	77.14 54	73.89 252	87.55 205	66.25 108	89.24 274	58.92 283	73.55 320	90.06 204

MIMVSNet		70.69 292	69.30 291	74.88 307	84.52 258	56.35 321	75.87 342	79.42 330	64.59 282	67.76 313	82.41 312	41.10 343	81.54 340	46.64 357	81.34 219	86.75 294

USDC		70.33 296	68.37 298	76.21 294	80.60 330	56.23 322	79.19 315	86.49 241	60.89 320	61.29 358	85.47 262	31.78 371	89.47 271	53.37 320	76.21 285	82.94 348

Baseline_NR-MVSNet		78.15 198	78.33 171	77.61 281	85.79 231	56.21 323	86.78 181	85.76 253	73.60 133	77.93 168	87.57 203	65.02 121	88.99 278	67.14 217	75.33 301	87.63 270

tpmvs		71.09 287	69.29 292	76.49 292	82.04 310	56.04 324	78.92 319	81.37 311	64.05 291	67.18 322	78.28 351	49.74 280	89.77 264	49.67 341	72.37 328	83.67 338

FC-MVSNet-test		81.52 116	82.02 100	80.03 240	88.42 166	55.97 325	87.95 146	93.42 29	77.10 56	77.38 177	90.98 122	69.96 68	91.79 217	68.46 205	84.50 172	92.33 119

GG-mvs-BLEND				75.38 303	81.59 317	55.80 326	79.32 312	69.63 373		67.19 321	73.67 371	43.24 329	88.90 283	50.41 333	84.50 172	81.45 357

VPNet		78.69 185	78.66 162	78.76 261	88.31 169	55.72 327	84.45 241	86.63 240	76.79 64	78.26 158	90.55 128	59.30 191	89.70 267	66.63 220	77.05 268	90.88 166

baseline1		76.98 225	76.75 212	77.66 279	88.13 173	55.66 328	85.12 223	81.89 305	73.04 148	76.79 191	88.90 167	62.43 149	87.78 297	63.30 244	71.18 337	89.55 224

test_vis1_rt		60.28 342	58.42 345	65.84 357	67.25 387	55.60 329	70.44 366	60.94 390	44.33 378	59.00 366	66.64 380	24.91 380	68.67 388	62.80 246	69.48 342	73.25 376

testing222		74.04 259	72.66 262	78.19 271	87.89 182	55.36 330	81.06 289	79.20 333	71.30 172	74.65 245	83.57 296	39.11 352	88.67 286	51.43 330	85.75 162	90.53 180

FMVSNet5		69.50 303	67.96 304	74.15 315	82.97 295	55.35 331	80.01 305	82.12 304	62.56 308	63.02 352	81.53 321	36.92 360	81.92 338	48.42 345	74.06 314	85.17 321

test_fmvs1_n		70.86 290	70.24 288	72.73 326	72.51 381	55.28 332	81.27 288	79.71 328	51.49 370	78.73 143	84.87 274	27.54 378	77.02 360	76.06 130	79.97 239	85.88 310

test_vis1_n		69.85 302	69.21 293	71.77 331	72.66 380	55.27 333	81.48 285	76.21 352	52.03 367	75.30 231	83.20 301	28.97 376	76.22 368	74.60 143	78.41 257	83.81 337

test_fmvs1		70.93 289	70.52 283	72.16 329	73.71 371	55.05 334	80.82 290	78.77 335	51.21 371	78.58 149	84.41 280	31.20 373	76.94 361	75.88 133	80.12 238	84.47 329

sss		73.60 264	73.64 254	73.51 319	82.80 297	55.01 335	76.12 338	81.69 308	62.47 309	74.68 244	85.85 253	57.32 207	78.11 355	60.86 268	80.93 224	87.39 276

mvsany_test1		62.30 339	61.26 343	65.41 358	69.52 383	54.86 336	66.86 377	49.78 398	46.65 375	68.50 311	83.21 300	49.15 288	66.28 390	56.93 303	60.77 368	75.11 374

ECVR-MVS		79.61 158	79.26 149	80.67 228	90.08 103	54.69 337	87.89 150	77.44 345	74.88 104	80.27 124	92.79 79	48.96 293	92.45 192	68.55 203	92.50 72	94.86 17

EPNet_dtu		75.46 247	74.86 238	77.23 287	82.57 303	54.60 338	86.89 176	83.09 291	71.64 162	66.25 335	85.86 252	55.99 214	88.04 294	54.92 312	86.55 148	89.05 237
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CP-MVSNet		78.22 194	78.34 170	77.84 276	87.83 186	54.54 339	87.94 147	91.17 116	77.65 38	73.48 257	88.49 180	62.24 153	88.43 289	62.19 254	74.07 313	90.55 179

gg-mvs-nofinetune		69.95 300	67.96 304	75.94 295	83.07 289	54.51 340	77.23 335	70.29 371	63.11 298	70.32 287	62.33 382	43.62 328	88.69 285	53.88 317	87.76 131	84.62 328

PS-CasMVS		78.01 203	78.09 175	77.77 278	87.71 192	54.39 341	88.02 143	91.22 113	77.50 46	73.26 259	88.64 175	60.73 178	88.41 290	61.88 258	73.88 317	90.53 180

Anonymous20240521		68.80 308	67.22 317	73.55 318	74.33 368	54.11 342	83.18 264	85.61 254	58.15 343	61.68 357	80.94 327	30.71 374	81.27 342	57.00 302	73.34 324	85.28 317

Patchmtry		70.74 291	69.16 294	75.49 302	80.72 328	54.07 343	74.94 351	80.30 322	58.34 341	70.01 292	81.19 322	52.50 242	86.54 304	53.37 320	71.09 338	85.87 311

PEN-MVS		77.73 209	77.69 190	77.84 276	87.07 214	53.91 344	87.91 149	91.18 115	77.56 43	73.14 261	88.82 170	61.23 171	89.17 275	59.95 273	72.37 328	90.43 184

gm-plane-assit					81.40 320	53.83 345			62.72 307		80.94 327		92.39 195	63.40 243

CL-MVSNet_self_test		72.37 278	71.46 272	75.09 305	79.49 347	53.53 346	80.76 293	85.01 261	69.12 224	70.51 284	82.05 318	57.92 200	84.13 324	52.27 325	66.00 357	87.60 271

MDTV_nov1_ep13			69.97 290		83.18 286	53.48 347	77.10 336	80.18 325	60.45 322	69.33 303	80.44 331	48.89 294	86.90 302	51.60 328	78.51 254

KD-MVS_2432*1600		66.22 328	63.89 330	73.21 320	75.47 366	53.42 348	70.76 364	84.35 269	64.10 289	66.52 331	78.52 349	34.55 366	84.98 318	50.40 334	50.33 384	81.23 358

miper_refine_blended		66.22 328	63.89 330	73.21 320	75.47 366	53.42 348	70.76 364	84.35 269	64.10 289	66.52 331	78.52 349	34.55 366	84.98 318	50.40 334	50.33 384	81.23 358

test1111		79.43 165	79.18 153	80.15 238	89.99 108	53.31 350	87.33 164	77.05 348	75.04 101	80.23 126	92.77 81	48.97 292	92.33 200	68.87 200	92.40 74	94.81 20

LF4IMVS		64.02 335	62.19 339	69.50 345	70.90 382	53.29 351	76.13 337	77.18 347	52.65 365	58.59 367	80.98 326	23.55 383	76.52 364	53.06 322	66.66 353	78.68 367

DTE-MVSNet		76.99 224	76.80 208	77.54 283	86.24 225	53.06 352	87.52 158	90.66 129	77.08 57	72.50 267	88.67 174	60.48 185	89.52 269	57.33 299	70.74 339	90.05 205

test2506		77.30 220	76.49 216	79.74 246	90.08 103	52.02 353	87.86 152	63.10 387	74.88 104	80.16 127	92.79 79	38.29 356	92.35 198	68.74 202	92.50 72	94.86 17

tpm		72.37 278	71.71 270	74.35 313	82.19 309	52.00 354	79.22 314	77.29 346	64.56 283	72.95 263	83.68 295	51.35 261	83.26 332	58.33 290	75.80 288	87.81 267

test_fmvs2		68.35 314	67.48 315	70.98 340	69.50 384	51.95 355	80.05 304	76.38 351	49.33 373	74.65 245	84.38 281	23.30 384	75.40 375	74.51 144	75.17 305	85.60 313

ETVMVS		72.25 280	71.05 278	75.84 296	87.77 191	51.91 356	79.39 311	74.98 356	69.26 217	73.71 254	82.95 304	40.82 346	86.14 308	46.17 359	84.43 177	89.47 225

WB-MVSnew		71.96 282	71.65 271	72.89 324	84.67 257	51.88 357	82.29 276	77.57 341	62.31 310	73.67 255	83.00 303	53.49 237	81.10 343	45.75 362	82.13 211	85.70 312

MIMVSNet1		68.58 310	66.78 320	73.98 316	80.07 337	51.82 358	80.77 292	84.37 268	64.40 285	59.75 365	82.16 317	36.47 361	83.63 328	42.73 370	70.33 340	86.48 298

Vis-MVSNet (Re-imp)		78.36 192	78.45 166	78.07 274	88.64 158	51.78 359	86.70 184	79.63 329	74.14 121	75.11 236	90.83 123	61.29 170	89.75 265	58.10 292	91.60 82	92.69 107

LCM-MVSNet-Re		77.05 223	76.94 205	77.36 284	87.20 211	51.60 360	80.06 303	80.46 320	75.20 97	67.69 315	86.72 226	62.48 147	88.98 279	63.44 242	89.25 114	91.51 143

Gipuma		45.18 360	41.86 363	55.16 373	77.03 359	51.52 361	32.50 395	80.52 318	32.46 391	27.12 394	35.02 395	9.52 398	75.50 372	22.31 394	60.21 371	38.45 394
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
UnsupCasMVSNet_eth		67.33 319	65.99 323	71.37 334	73.48 374	51.47 362	75.16 347	85.19 258	65.20 275	60.78 360	80.93 329	42.35 334	77.20 359	57.12 300	53.69 380	85.44 315

UnsupCasMVSNet_bld		63.70 336	61.53 342	70.21 343	73.69 372	51.39 363	72.82 356	81.89 305	55.63 358	57.81 371	71.80 375	38.67 353	78.61 352	49.26 343	52.21 382	80.63 361

FPMVS		53.68 350	51.64 352	59.81 365	65.08 389	51.03 364	69.48 369	69.58 374	41.46 381	40.67 387	72.32 374	16.46 391	70.00 387	24.24 393	65.42 358	58.40 389

CVMVSNet		72.99 273	72.58 263	74.25 314	84.28 261	50.85 365	86.41 191	83.45 285	44.56 377	73.23 260	87.54 206	49.38 284	85.70 311	65.90 226	78.44 255	86.19 302

Anonymous20231206		68.60 309	67.80 309	71.02 339	80.23 335	50.75 366	78.30 327	80.47 319	56.79 353	66.11 336	82.63 311	46.35 308	78.95 351	43.62 368	75.70 289	83.36 341

ambc				75.24 304	73.16 376	50.51 367	63.05 387	87.47 225		64.28 346	77.81 355	17.80 389	89.73 266	57.88 294	60.64 369	85.49 314

APD_test1		53.31 351	49.93 356	63.42 361	65.68 388	50.13 368	71.59 360	66.90 380	34.43 389	40.58 388	71.56 376	8.65 400	76.27 367	34.64 383	55.36 378	63.86 385

tpmrst		72.39 276	72.13 267	73.18 323	80.54 331	49.91 369	79.91 307	79.08 334	63.11 298	71.69 277	79.95 336	55.32 216	82.77 334	65.66 229	73.89 316	86.87 290

Patchmatch-test		64.82 333	63.24 334	69.57 344	79.42 348	49.82 370	63.49 386	69.05 376	51.98 368	59.95 364	80.13 334	50.91 265	70.98 384	40.66 374	73.57 319	87.90 265

EPMVS		69.02 306	68.16 301	71.59 332	79.61 345	49.80 371	77.40 333	66.93 379	62.82 305	70.01 292	79.05 343	45.79 315	77.86 357	56.58 306	75.26 303	87.13 285

dp		66.80 322	65.43 324	70.90 341	79.74 344	48.82 372	75.12 349	74.77 358	59.61 330	64.08 348	77.23 357	42.89 331	80.72 345	48.86 344	66.58 354	83.16 343

test0.0.03 1		68.00 316	67.69 311	68.90 348	77.55 355	47.43 373	75.70 343	72.95 367	66.66 256	66.56 329	82.29 315	48.06 296	75.87 370	44.97 366	74.51 311	83.41 340

ADS-MVSNet		64.36 334	62.88 337	68.78 350	79.92 338	47.17 374	67.55 375	71.18 369	53.37 363	65.25 341	75.86 364	42.32 335	73.99 380	41.57 372	68.91 346	85.18 319

EU-MVSNet		68.53 312	67.61 313	71.31 337	78.51 353	47.01 375	84.47 238	84.27 272	42.27 380	66.44 334	84.79 276	40.44 347	83.76 326	58.76 286	68.54 349	83.17 342

test_fmvs3		63.36 337	61.82 340	67.98 353	62.51 391	46.96 376	77.37 334	74.03 362	45.24 376	67.50 317	78.79 348	12.16 395	72.98 383	72.77 164	66.02 356	83.99 335

KD-MVS_self_test		68.81 307	67.59 314	72.46 328	74.29 369	45.45 377	77.93 330	87.00 234	63.12 297	63.99 349	78.99 347	42.32 335	84.77 321	56.55 307	64.09 362	87.16 284

testf1		45.72 358	41.96 361	57.00 367	56.90 393	45.32 378	66.14 380	59.26 392	26.19 393	30.89 392	60.96 386	4.14 403	70.64 385	26.39 391	46.73 388	55.04 390

APD_test2		45.72 358	41.96 361	57.00 367	56.90 393	45.32 378	66.14 380	59.26 392	26.19 393	30.89 392	60.96 386	4.14 403	70.64 385	26.39 391	46.73 388	55.04 390

LCM-MVSNet		54.25 347	49.68 357	67.97 354	53.73 399	45.28 380	66.85 378	80.78 314	35.96 388	39.45 389	62.23 384	8.70 399	78.06 356	48.24 349	51.20 383	80.57 362

test_vis3_rt		49.26 357	47.02 359	56.00 369	54.30 396	45.27 381	66.76 379	48.08 399	36.83 386	44.38 386	53.20 391	7.17 402	64.07 392	56.77 305	55.66 376	58.65 388

test20.03		67.45 318	66.95 319	68.94 347	75.48 365	44.84 382	77.50 332	77.67 340	66.66 256	63.01 353	83.80 291	47.02 302	78.40 353	42.53 371	68.86 348	83.58 339

mvsany_test3		53.99 348	51.45 353	61.61 363	55.51 395	44.74 383	63.52 385	45.41 402	43.69 379	58.11 370	76.45 361	17.99 388	63.76 393	54.77 313	47.59 386	76.34 372

PatchT		68.46 313	67.85 306	70.29 342	80.70 329	43.93 384	72.47 357	74.88 357	60.15 326	70.55 283	76.57 360	49.94 277	81.59 339	50.58 332	74.83 308	85.34 316

MVS-HIRNet		59.14 343	57.67 346	63.57 360	81.65 315	43.50 385	71.73 359	65.06 384	39.59 384	51.43 381	57.73 388	38.34 355	82.58 335	39.53 375	73.95 315	64.62 384

testing3		68.56 311	67.67 312	71.22 338	87.33 208	42.87 386	83.06 270	71.54 368	70.36 191	69.08 305	84.38 281	30.33 375	85.69 312	37.50 380	75.45 297	85.09 323

WAC-MVS						42.58 387								39.46 376

myMVS_eth3d		67.02 321	66.29 322	69.21 346	84.68 254	42.58 387	78.62 322	73.08 365	66.65 259	66.74 327	79.46 340	31.53 372	82.30 336	39.43 377	76.38 282	82.75 349

PMVS	37.38 22	44.16 361	40.28 364	55.82 371	40.82 404	42.54 389	65.12 383	63.99 386	34.43 389	24.48 395	57.12 390	3.92 405	76.17 369	17.10 397	55.52 377	48.75 392
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_f		52.09 353	50.82 354	55.90 370	53.82 398	42.31 390	59.42 388	58.31 394	36.45 387	56.12 377	70.96 377	12.18 394	57.79 395	53.51 319	56.57 375	67.60 381

testgi		66.67 324	66.53 321	67.08 356	75.62 364	41.69 391	75.93 339	76.50 350	66.11 265	65.20 343	86.59 234	35.72 364	74.71 377	43.71 367	73.38 323	84.84 325

Syy-MVS		68.05 315	67.85 306	68.67 351	84.68 254	40.97 392	78.62 322	73.08 365	66.65 259	66.74 327	79.46 340	52.11 250	82.30 336	32.89 384	76.38 282	82.75 349

ANet_high		50.57 356	46.10 360	63.99 359	48.67 402	39.13 393	70.99 363	80.85 313	61.39 318	31.18 391	57.70 389	17.02 390	73.65 382	31.22 386	15.89 399	79.18 366

MDTV_nov1_ep13_2view						37.79 394	75.16 347		55.10 359	66.53 330		49.34 285		53.98 316		87.94 264

DSMNet-mixed		57.77 345	56.90 347	60.38 364	67.70 386	35.61 395	69.18 370	53.97 396	32.30 392	57.49 372	79.88 337	40.39 348	68.57 389	38.78 378	72.37 328	76.97 370

MVE	26.22 23	30.37 366	25.89 370	43.81 378	44.55 403	35.46 396	28.87 396	39.07 403	18.20 397	18.58 399	40.18 394	2.68 406	47.37 400	17.07 398	23.78 396	48.60 393
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
new_pmnet		50.91 355	50.29 355	52.78 375	68.58 385	34.94 397	63.71 384	56.63 395	39.73 383	44.95 385	65.47 381	21.93 385	58.48 394	34.98 382	56.62 374	64.92 383

wuyk23d		16.82 369	15.94 372	19.46 383	58.74 392	31.45 398	39.22 393	3.74 408	6.84 399	6.04 402	2.70 402	1.27 407	24.29 402	10.54 402	14.40 401	2.63 399

E-PMN		31.77 363	30.64 366	35.15 380	52.87 400	27.67 399	57.09 390	47.86 400	24.64 395	16.40 400	33.05 396	11.23 396	54.90 397	14.46 400	18.15 397	22.87 396

DeepMVS_CX				27.40 382	40.17 405	26.90 400		24.59 406	17.44 398	23.95 396	48.61 393	9.77 397	26.48 401	18.06 395	24.47 395	28.83 395

EMVS		30.81 365	29.65 367	34.27 381	50.96 401	25.95 401	56.58 391	46.80 401	24.01 396	15.53 401	30.68 397	12.47 393	54.43 398	12.81 401	17.05 398	22.43 397

dmvs_testset		62.63 338	64.11 329	58.19 366	78.55 352	24.76 402	75.28 345	65.94 382	67.91 245	60.34 361	76.01 363	53.56 235	73.94 381	31.79 385	67.65 350	75.88 373

new-patchmatchnet		61.73 340	61.73 341	61.70 362	72.74 379	24.50 403	69.16 371	78.03 338	61.40 317	56.72 374	75.53 367	38.42 354	76.48 365	45.95 361	57.67 372	84.13 333

WB-MVS		54.94 346	54.72 348	55.60 372	73.50 373	20.90 404	74.27 353	61.19 389	59.16 335	50.61 382	74.15 369	47.19 301	75.78 371	17.31 396	35.07 391	70.12 379

SSC-MVS		53.88 349	53.59 350	54.75 374	72.87 378	19.59 405	73.84 355	60.53 391	57.58 349	49.18 384	73.45 372	46.34 309	75.47 374	16.20 399	32.28 393	69.20 380

PMMVS2		40.82 362	38.86 365	46.69 377	53.84 397	16.45 406	48.61 392	49.92 397	37.49 385	31.67 390	60.97 385	8.14 401	56.42 396	28.42 388	30.72 394	67.19 382

tmp_tt		18.61 368	21.40 371	10.23 384	4.82 407	10.11 407	34.70 394	30.74 405	1.48 401	23.91 397	26.07 398	28.42 377	13.41 403	27.12 389	15.35 400	7.17 398

N_pmnet		52.79 352	53.26 351	51.40 376	78.99 351	7.68 408	69.52 368	3.89 407	51.63 369	57.01 373	74.98 368	40.83 345	65.96 391	37.78 379	64.67 360	80.56 363

test_method		31.52 364	29.28 368	38.23 379	27.03 406	6.50 409	20.94 397	62.21 388	4.05 400	22.35 398	52.50 392	13.33 392	47.58 399	27.04 390	34.04 392	60.62 386

test123		6.12 371	8.11 374	0.14 385	0.06 409	0.09 410	71.05 362	0.03 410	0.04 404	0.25 405	1.30 404	0.05 408	0.03 405	0.21 404	0.01 403	0.29 400

testmvs		6.04 372	8.02 375	0.10 386	0.08 408	0.03 411	69.74 367	0.04 409	0.05 403	0.31 404	1.68 403	0.02 409	0.04 404	0.24 403	0.02 402	0.25 401

test_blank		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

uanet_test		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

DCPMVS		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

cdsmvs_eth3d_5k		19.96 367	26.61 369	0.00 387	0.00 410	0.00 412	0.00 398	89.26 173	0.00 405	0.00 406	88.61 176	61.62 161	0.00 406	0.00 405	0.00 404	0.00 402

pcd_1.5k_mvsjas		5.26 373	7.02 376	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	63.15 138	0.00 406	0.00 405	0.00 404	0.00 402

sosnet-low-res		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

sosnet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

uncertanet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

Regformer		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

ab-mvs-re		7.23 370	9.64 373	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	86.72 226	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

uanet		0.00 374	0.00 377	0.00 387	0.00 410	0.00 412	0.00 398	0.00 411	0.00 405	0.00 406	0.00 405	0.00 410	0.00 406	0.00 405	0.00 404	0.00 402

PC_three_1452									68.21 242	92.02 12	94.00 46	82.09 5	95.98 51	84.58 48	96.68 2	94.95 10

eth-test2					0.00 410

eth-test					0.00 410

test_241102_TWO								94.06 10	77.24 50	92.78 4	95.72 8	81.26 8	97.44 6	89.07 14	96.58 6	94.26 41

9.14			88.26 15		92.84 60		91.52 46	94.75 1	73.93 125	88.57 22	94.67 19	75.57 22	95.79 53	86.77 35	95.76 23

test_0728_THIRD									78.38 33	92.12 9	95.78 4	81.46 7	97.40 8	89.42 9	96.57 7	94.67 24

GSMVS																88.96 243

sam_mvs1												51.32 262				88.96 243

sam_mvs												50.01 275

MTGPA								92.02 85

test_post1							78.90 320				5.43 401	48.81 295	85.44 316	59.25 279

test_post											5.46 400	50.36 273	84.24 323

patchmatchnet-post											74.00 370	51.12 264	88.60 287

MTMP							92.18 35	32.83 404

test9_res														84.90 42	95.70 26	92.87 102

agg_prior2														82.91 66	95.45 30	92.70 105

test_prior2							88.85 111		75.41 93	84.91 59	93.54 56	74.28 29		83.31 61	95.86 20

旧先验2							86.56 188		58.10 344	87.04 39			88.98 279	74.07 149

新几何2							86.29 196

无先验							87.48 159	88.98 186	60.00 327				94.12 121	67.28 214		88.97 242

原ACMM2							86.86 177

testdata2													91.01 249	62.37 253

segment_acmp												73.08 37

testdata1							84.14 249		75.71 87

plane_prior5								92.44 69					95.38 69	78.71 102	86.32 151	91.33 149

plane_prior4											91.00 120

plane_prior2							91.25 50		79.12 23

plane_prior1					89.90 111

n2								0.00 411

nn								0.00 411

door-mid								69.98 372

test11								92.23 79

door								69.44 375

HQP-NCC					89.33 128		89.17 98		76.41 72	77.23 182

ACMP_Plane					89.33 128		89.17 98		76.41 72	77.23 182

BP-MVS														77.47 114

HQP4-MVS										77.24 181			95.11 80			91.03 161

HQP3-MVS								92.19 82							85.99 158

HQP2-MVS												60.17 189

ACMMP++_ref															81.95 214

ACMMP++															81.25 220

Test By Simon												64.33 125

High-resolution multi-view benchmark