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.

DVP-MVS++		81.24 35	82.74 37	76.76 82	83.14 96	60.90 145	91.64 1	85.49 29	74.03 21	84.93 56	90.38 64	66.82 108	85.90 38	77.43 30	90.78 114	83.49 139

FOURS1					89.19 23	77.84 12	91.64 1	89.11 2	84.05 2	91.57 2

LTVRE_ROB	75.46 1	84.22 6	84.98 7	81.94 20	84.82 73	75.40 25	91.60 3	87.80 7	73.52 24	88.90 11	93.06 6	71.39 68	81.53 114	81.53 3	92.15 82	88.91 38
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
TDRefinement		86.32 2	86.33 2	86.29 1	88.64 31	81.19 4	88.84 4	90.72 1	78.27 8	87.95 14	92.53 13	79.37 13	84.79 66	74.51 48	96.15 2	92.88 7

CP-MVS		84.12 8	84.55 10	82.80 10	89.42 17	79.74 5	88.19 5	84.43 57	71.96 38	84.70 61	90.56 52	77.12 25	86.18 26	79.24 17	95.36 12	82.49 173

ACMMP		84.22 6	84.84 8	82.35 17	89.23 21	76.66 22	87.65 6	85.89 25	71.03 42	85.85 42	90.58 51	78.77 16	85.78 42	79.37 15	95.17 16	84.62 106
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
LS3D		80.99 41	80.85 49	81.41 25	78.37 162	71.37 50	87.45 7	85.87 26	77.48 12	81.98 91	89.95 78	69.14 86	85.26 54	66.15 110	91.24 96	87.61 52

SR-MVS-dyc-post		84.75 3	85.26 5	83.21 3	86.19 49	79.18 6	87.23 8	86.27 19	77.51 10	87.65 18	90.73 47	79.20 14	85.58 49	78.11 23	94.46 36	84.89 95

RE-MVS-def			85.50 3		86.19 49	79.18 6	87.23 8	86.27 19	77.51 10	87.65 18	90.73 47	81.38 7		78.11 23	94.46 36	84.89 95

COLMAP_ROB	72.78 3	83.75 11	84.11 15	82.68 12	82.97 104	74.39 32	87.18 10	88.18 6	78.98 6	86.11 40	91.47 30	79.70 12	85.76 43	66.91 108	95.46 11	87.89 48
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MSP-MVS		80.49 45	79.67 58	82.96 5	89.70 11	77.46 19	87.16 11	85.10 39	64.94 89	81.05 105	88.38 114	57.10 210	87.10 8	79.75 7	83.87 228	84.31 121
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
mPP-MVS		84.01 10	84.39 11	82.88 6	90.65 3	81.38 3	87.08 12	82.79 82	72.41 34	85.11 55	90.85 44	76.65 28	84.89 63	79.30 16	94.63 33	82.35 175

region2R		83.54 14	83.86 19	82.58 14	89.82 9	77.53 16	87.06 13	84.23 63	70.19 48	83.86 71	90.72 49	75.20 40	86.27 21	79.41 14	94.25 50	83.95 128

HFP-MVS		83.39 17	84.03 16	81.48 23	89.25 20	75.69 24	87.01 14	84.27 60	70.23 46	84.47 64	90.43 57	76.79 26	85.94 35	79.58 10	94.23 51	82.82 164

ACMMPR		83.62 12	83.93 17	82.69 11	89.78 10	77.51 18	87.01 14	84.19 64	70.23 46	84.49 63	90.67 50	75.15 41	86.37 18	79.58 10	94.26 49	84.18 124

SR-MVS		84.51 5	85.27 4	82.25 18	88.52 33	77.71 13	86.81 16	85.25 36	77.42 13	86.15 38	90.24 71	81.69 5	85.94 35	77.77 26	93.58 61	83.09 155

XVS		83.51 15	83.73 20	82.85 8	89.43 15	77.61 14	86.80 17	84.66 52	72.71 27	82.87 82	90.39 62	73.86 52	86.31 19	78.84 19	94.03 53	84.64 104

X-MVStestdata		76.81 77	74.79 100	82.85 8	89.43 15	77.61 14	86.80 17	84.66 52	72.71 27	82.87 82	9.95 396	73.86 52	86.31 19	78.84 19	94.03 53	84.64 104

TSAR-MVS + MP.		79.05 57	78.81 62	79.74 42	88.94 27	67.52 83	86.61 19	81.38 105	51.71 222	77.15 147	91.42 32	65.49 124	87.20 6	79.44 13	87.17 184	84.51 116
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
APDe-MVS		82.88 23	84.14 14	79.08 53	84.80 75	66.72 90	86.54 20	85.11 38	72.00 37	86.65 31	91.75 24	78.20 20	87.04 9	77.93 25	94.32 48	83.47 142
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CPTT-MVS		81.51 34	81.76 43	80.76 34	89.20 22	78.75 9	86.48 21	82.03 93	68.80 53	80.92 107	88.52 110	72.00 63	82.39 100	74.80 44	93.04 68	81.14 193

MP-MVS		83.19 18	83.54 23	82.14 19	90.54 4	79.00 8	86.42 22	83.59 73	71.31 39	81.26 102	90.96 39	74.57 47	84.69 67	78.41 21	94.78 27	82.74 167
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		83.12 20	83.68 21	81.45 24	89.14 24	73.28 42	86.32 23	85.97 24	67.39 60	84.02 68	90.39 62	74.73 45	86.46 15	80.73 6	94.43 40	84.60 109

HPM-MVS_fast		84.59 4	85.10 6	83.06 4	88.60 32	75.83 23	86.27 24	86.89 15	73.69 23	86.17 37	91.70 25	78.23 19	85.20 58	79.45 12	94.91 24	88.15 47

GST-MVS		82.79 24	83.27 29	81.34 27	88.99 26	73.29 41	85.94 25	85.13 37	68.58 57	84.14 67	90.21 73	73.37 56	86.41 16	79.09 18	93.98 56	84.30 123

SteuartSystems-ACMMP		83.07 21	83.64 22	81.35 26	85.14 68	71.00 54	85.53 26	84.78 45	70.91 43	85.64 45	90.41 59	75.55 38	87.69 4	79.75 7	95.08 19	85.36 85
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS_3200maxsize		83.57 13	84.33 12	81.31 28	82.83 107	73.53 40	85.50 27	87.45 12	74.11 19	86.45 35	90.52 55	80.02 10	84.48 70	77.73 27	94.34 47	85.93 74

HPM-MVS		84.12 8	84.63 9	82.60 13	88.21 35	74.40 31	85.24 28	87.21 13	70.69 45	85.14 54	90.42 58	78.99 15	86.62 13	80.83 5	94.93 23	86.79 63
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SMA-MVS		82.12 28	82.68 38	80.43 36	88.90 29	69.52 65	85.12 29	84.76 46	63.53 102	84.23 66	91.47 30	72.02 62	87.16 7	79.74 9	94.36 45	84.61 107
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
MTAPA		83.19 18	83.87 18	81.13 30	91.16 2	78.16 11	84.87 30	80.63 123	72.08 36	84.93 56	90.79 45	74.65 46	84.42 72	80.98 4	94.75 28	80.82 203

MTMP							84.83 31	19.26 403

LCM-MVSNet		86.90 1	88.67 1	81.57 21	91.50 1	63.30 120	84.80 32	87.77 9	86.18 1	96.26 1	96.06 1	90.32 1	84.49 69	68.08 89	97.05 1	96.93 1

UA-Net		81.56 33	82.28 40	79.40 50	88.91 28	69.16 72	84.67 33	80.01 137	75.34 15	79.80 118	94.91 2	69.79 83	80.25 141	72.63 63	94.46 36	88.78 42

3Dnovator+	73.19 2	81.08 39	80.48 51	82.87 7	81.41 125	72.03 45	84.38 34	86.23 22	77.28 14	80.65 111	90.18 74	59.80 181	87.58 5	73.06 59	91.34 94	89.01 34

EGC-MVSNET		64.77 233	61.17 266	75.60 98	86.90 42	74.47 30	84.04 35	68.62 263	0.60 398	1.13 400	91.61 28	65.32 127	74.15 230	64.01 128	88.28 160	78.17 245

MVSFormer		69.93 167	69.03 179	72.63 152	74.93 209	59.19 159	83.98 36	75.72 198	52.27 214	63.53 319	76.74 290	43.19 286	80.56 134	72.28 67	78.67 285	78.14 246

test_djsdf		78.88 59	78.27 69	80.70 35	81.42 124	71.24 52	83.98 36	75.72 198	52.27 214	87.37 26	92.25 16	68.04 97	80.56 134	72.28 67	91.15 99	90.32 22

APD-MVS		81.13 38	81.73 44	79.36 51	84.47 80	70.53 59	83.85 38	83.70 71	69.43 52	83.67 73	88.96 100	75.89 34	86.41 16	72.62 64	92.95 69	81.14 193
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test0726					86.16 51	60.78 148	83.81 39	85.10 39	72.48 32	85.27 53	89.96 77	78.57 17

DVP-MVS		81.15 37	83.12 32	75.24 103	86.16 51	60.78 148	83.77 40	80.58 125	72.48 32	85.83 43	90.41 59	78.57 17	85.69 45	75.86 39	94.39 41	79.24 231
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				76.57 85	86.20 48	60.57 151	83.77 40	85.49 29					85.90 38	75.86 39	94.39 41	83.25 150

SED-MVS		81.78 31	83.48 24	76.67 83	86.12 53	61.06 141	83.62 42	84.72 48	72.61 30	87.38 24	89.70 81	77.48 23	85.89 40	75.29 42	94.39 41	83.08 156

OPU-MVS				78.65 62	83.44 94	66.85 89	83.62 42				86.12 163	66.82 108	86.01 31	61.72 149	89.79 135	83.08 156

ACMMP_NAP		82.33 27	83.28 28	79.46 49	89.28 18	69.09 74	83.62 42	84.98 41	64.77 90	83.97 69	91.02 38	75.53 39	85.93 37	82.00 2	94.36 45	83.35 148

HPM-MVS++		79.89 51	79.80 57	80.18 39	89.02 25	78.44 10	83.49 45	80.18 134	64.71 91	78.11 136	88.39 113	65.46 125	83.14 89	77.64 29	91.20 97	78.94 235

SF-MVS		80.72 43	81.80 42	77.48 74	82.03 117	64.40 112	83.41 46	88.46 5	65.28 81	84.29 65	89.18 92	73.73 55	83.22 88	76.01 38	93.77 58	84.81 101

SD-MVS		80.28 49	81.55 47	76.47 88	83.57 90	67.83 80	83.39 47	85.35 35	64.42 92	86.14 39	87.07 130	74.02 51	80.97 128	77.70 28	92.32 80	80.62 211
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
RRT_MVS		78.18 68	77.69 73	79.66 46	83.14 96	61.34 136	83.29 48	80.34 132	57.43 154	86.65 31	91.79 23	50.52 245	86.01 31	71.36 70	94.65 32	91.62 11

ACMM	69.25 9	82.11 29	83.31 27	78.49 64	88.17 36	73.96 34	83.11 49	84.52 56	66.40 69	87.45 22	89.16 94	81.02 8	80.52 137	74.27 51	95.73 7	80.98 199
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DPE-MVS		82.00 30	83.02 33	78.95 58	85.36 65	67.25 85	82.91 50	84.98 41	73.52 24	85.43 51	90.03 75	76.37 29	86.97 11	74.56 47	94.02 55	82.62 170
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
HQP_MVS		78.77 60	78.78 64	78.72 60	85.18 66	65.18 104	82.74 51	85.49 29	65.45 76	78.23 133	89.11 95	60.83 170	86.15 27	71.09 71	90.94 106	84.82 99

plane_prior2							82.74 51		65.45 76

ACMP	69.50 8	82.64 25	83.38 26	80.40 37	86.50 45	69.44 67	82.30 53	86.08 23	66.80 65	86.70 30	89.99 76	81.64 6	85.95 34	74.35 50	96.11 3	85.81 76
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PMVS	70.70 6	81.70 32	83.15 31	77.36 77	90.35 5	82.82 2	82.15 54	79.22 150	74.08 20	87.16 28	91.97 19	84.80 2	76.97 196	64.98 121	93.61 60	72.28 298
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepC-MVS	72.44 4	81.00 40	80.83 50	81.50 22	86.70 44	70.03 64	82.06 55	87.00 14	59.89 130	80.91 108	90.53 53	72.19 60	88.56 1	73.67 55	94.52 35	85.92 75
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PGM-MVS		83.07 21	83.25 30	82.54 15	89.57 13	77.21 20	82.04 56	85.40 33	67.96 59	84.91 59	90.88 42	75.59 36	86.57 14	78.16 22	94.71 30	83.82 130

LPG-MVS_test		83.47 16	84.33 12	80.90 32	87.00 39	70.41 60	82.04 56	86.35 16	69.77 50	87.75 15	91.13 34	81.83 3	86.20 24	77.13 35	95.96 5	86.08 71

F-COLMAP		75.29 91	73.99 111	79.18 52	81.73 121	71.90 46	81.86 58	82.98 79	59.86 131	72.27 226	84.00 190	64.56 133	83.07 92	51.48 234	87.19 183	82.56 172

MP-MVS-pluss		82.54 26	83.46 25	79.76 41	88.88 30	68.44 76	81.57 59	86.33 18	63.17 108	85.38 52	91.26 33	76.33 30	84.67 68	83.30 1	94.96 22	86.17 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PAPM_NR		73.91 108	74.16 109	73.16 131	81.90 119	53.50 198	81.28 60	81.40 104	66.17 70	73.30 213	83.31 203	59.96 177	83.10 91	58.45 180	81.66 255	82.87 162

API-MVS		70.97 156	71.51 157	69.37 196	75.20 206	55.94 181	80.99 61	76.84 188	62.48 113	71.24 242	77.51 285	61.51 159	80.96 131	52.04 230	85.76 201	71.22 308

MM				79.55 48		65.47 100	80.94 62	78.74 160	71.22 40	72.40 225	88.70 105	60.51 172	87.70 3	77.40 32	89.13 151	85.48 84

OMC-MVS		79.41 55	78.79 63	81.28 29	80.62 132	70.71 58	80.91 63	84.76 46	62.54 112	81.77 94	86.65 145	71.46 66	83.53 83	67.95 93	92.44 76	89.60 24

CS-MVS		76.51 79	76.00 89	78.06 71	77.02 180	64.77 109	80.78 64	82.66 85	60.39 126	74.15 199	83.30 204	69.65 84	82.07 107	69.27 82	86.75 190	87.36 55

mvs_tets		78.93 58	78.67 65	79.72 43	84.81 74	73.93 35	80.65 65	76.50 191	51.98 219	87.40 23	91.86 21	76.09 33	78.53 167	68.58 84	90.20 123	86.69 66

mvsmamba		77.20 74	76.37 84	79.69 45	80.34 135	61.52 133	80.58 66	82.12 91	53.54 205	83.93 70	91.03 37	49.49 251	85.97 33	73.26 57	93.08 67	91.59 12

ACMH+	66.64 10	81.20 36	82.48 39	77.35 78	81.16 129	62.39 125	80.51 67	87.80 7	73.02 26	87.57 20	91.08 36	80.28 9	82.44 99	64.82 122	96.10 4	87.21 57

EPP-MVSNet		73.86 110	73.38 122	75.31 101	78.19 164	53.35 200	80.45 68	77.32 183	65.11 85	76.47 168	86.80 135	49.47 252	83.77 77	53.89 221	92.72 74	88.81 41

jajsoiax		78.51 63	78.16 70	79.59 47	84.65 77	73.83 37	80.42 69	76.12 193	51.33 230	87.19 27	91.51 29	73.79 54	78.44 171	68.27 87	90.13 127	86.49 68

PHI-MVS		74.92 99	74.36 106	76.61 84	76.40 191	62.32 126	80.38 70	83.15 77	54.16 195	73.23 214	80.75 236	62.19 152	83.86 76	68.02 90	90.92 109	83.65 136

QAPM		69.18 179	69.26 175	68.94 208	71.61 257	52.58 204	80.37 71	78.79 159	49.63 249	73.51 208	85.14 177	53.66 228	79.12 157	55.11 206	75.54 305	75.11 275

9.14			80.22 53		80.68 131		80.35 72	87.69 10	59.90 129	83.00 79	88.20 117	74.57 47	81.75 112	73.75 54	93.78 57

EC-MVSNet		77.08 76	77.39 76	76.14 92	76.86 188	56.87 177	80.32 73	87.52 11	63.45 104	74.66 191	84.52 183	69.87 82	84.94 61	69.76 79	89.59 139	86.60 67

OurMVSNet-221017-0		78.57 62	78.53 67	78.67 61	80.48 133	64.16 113	80.24 74	82.06 92	61.89 116	88.77 12	93.32 4	57.15 208	82.60 98	70.08 77	92.80 71	89.25 28

XVG-ACMP-BASELINE		80.54 44	81.06 48	78.98 57	87.01 38	72.91 43	80.23 75	85.56 28	66.56 68	85.64 45	89.57 83	69.12 87	80.55 136	72.51 65	93.37 63	83.48 141

MVS_0304		76.32 81	75.96 91	77.42 76	79.33 145	60.86 147	80.18 76	74.88 205	66.93 62	69.11 265	88.95 101	57.84 204	86.12 29	76.63 37	89.77 136	85.28 86

anonymousdsp		78.60 61	77.80 72	81.00 31	78.01 168	74.34 33	80.09 77	76.12 193	50.51 240	89.19 10	90.88 42	71.45 67	77.78 189	73.38 56	90.60 119	90.90 18

Gipuma		69.55 173	72.83 134	59.70 297	63.63 336	53.97 195	80.08 78	75.93 196	64.24 94	73.49 209	88.93 102	57.89 203	62.46 321	59.75 172	91.55 91	62.67 360
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
plane_prior						65.18 104	80.06 79		61.88 117						89.91 132

DeepC-MVS_fast	69.89 7	77.17 75	76.33 86	79.70 44	83.90 88	67.94 78	80.06 79	83.75 70	56.73 161	74.88 186	85.32 174	65.54 123	87.79 2	65.61 117	91.14 100	83.35 148
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		78.25 67	78.04 71	78.89 59	85.61 62	69.45 66	79.80 81	80.99 116	65.77 72	75.55 177	86.25 158	67.42 101	85.42 50	70.10 76	90.88 112	81.81 185

IS-MVSNet		75.10 95	75.42 97	74.15 115	79.23 148	48.05 243	79.43 82	78.04 174	70.09 49	79.17 124	88.02 122	53.04 231	83.60 81	58.05 183	93.76 59	90.79 19

AdaColmap		74.22 106	74.56 102	73.20 130	81.95 118	60.97 143	79.43 82	80.90 117	65.57 74	72.54 223	81.76 225	70.98 73	85.26 54	47.88 269	90.00 128	73.37 286

OPM-MVS		80.99 41	81.63 46	79.07 54	86.86 43	69.39 68	79.41 84	84.00 69	65.64 73	85.54 49	89.28 87	76.32 31	83.47 84	74.03 52	93.57 62	84.35 120
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
save fliter					87.00 39	67.23 86	79.24 85	77.94 176	56.65 163

v7n		79.37 56	80.41 52	76.28 90	78.67 161	55.81 183	79.22 86	82.51 88	70.72 44	87.54 21	92.44 14	68.00 98	81.34 116	72.84 61	91.72 84	91.69 10

DP-MVS		78.44 66	79.29 60	75.90 94	81.86 120	65.33 102	79.05 87	84.63 54	74.83 18	80.41 113	86.27 156	71.68 64	83.45 85	62.45 145	92.40 77	78.92 236

CS-MVS-test		74.89 102	74.23 108	76.86 81	77.01 181	62.94 123	78.98 88	84.61 55	58.62 141	70.17 254	80.80 235	66.74 112	81.96 108	61.74 148	89.40 145	85.69 81

ACMH	63.62 14	77.50 72	80.11 54	69.68 193	79.61 140	56.28 179	78.81 89	83.62 72	63.41 106	87.14 29	90.23 72	76.11 32	73.32 236	67.58 95	94.44 39	79.44 229
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
bld_raw_dy_0_64		72.85 134	72.76 136	73.09 134	85.08 70	64.80 108	78.72 90	64.22 293	51.92 220	83.13 77	90.26 70	39.21 312	69.91 272	70.73 73	91.60 89	84.56 111

MSLP-MVS++		74.48 105	75.78 92	70.59 175	84.66 76	62.40 124	78.65 91	84.24 62	60.55 125	77.71 142	81.98 221	63.12 140	77.64 191	62.95 142	88.14 162	71.73 303

AllTest		77.66 70	77.43 75	78.35 66	79.19 150	70.81 55	78.60 92	88.64 3	65.37 79	80.09 116	88.17 118	70.33 76	78.43 172	55.60 201	90.90 110	85.81 76

PS-MVSNAJss		77.54 71	77.35 77	78.13 70	84.88 72	66.37 92	78.55 93	79.59 144	53.48 206	86.29 36	92.43 15	62.39 149	80.25 141	67.90 94	90.61 118	87.77 49

Effi-MVS+-dtu		75.43 90	72.28 145	84.91 2	77.05 178	83.58 1	78.47 94	77.70 178	57.68 149	74.89 185	78.13 279	64.80 131	84.26 74	56.46 194	85.32 207	86.88 62

3Dnovator	65.95 11	71.50 150	71.22 160	72.34 158	73.16 239	63.09 121	78.37 95	78.32 168	57.67 150	72.22 228	84.61 181	54.77 221	78.47 169	60.82 159	81.07 259	75.45 270

OpenMVS	62.51 15	68.76 184	68.75 184	68.78 213	70.56 268	53.91 196	78.29 96	77.35 182	48.85 256	70.22 252	83.52 196	52.65 233	76.93 197	55.31 205	81.99 245	75.49 269

WR-MVS_H		80.22 50	82.17 41	74.39 111	89.46 14	42.69 294	78.24 97	82.24 89	78.21 9	89.57 9	92.10 18	68.05 96	85.59 48	66.04 113	95.62 9	94.88 5

114514_t		73.40 116	73.33 125	73.64 123	84.15 86	57.11 175	78.20 98	80.02 136	43.76 295	72.55 222	86.07 166	64.00 136	83.35 87	60.14 166	91.03 105	80.45 214

PLC	62.01 16	71.79 148	70.28 168	76.33 89	80.31 136	68.63 75	78.18 99	81.24 108	54.57 186	67.09 293	80.63 238	59.44 182	81.74 113	46.91 276	84.17 225	78.63 237
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNVR-MVS		78.49 64	78.59 66	78.16 68	85.86 60	67.40 84	78.12 100	81.50 101	63.92 96	77.51 144	86.56 149	68.43 93	84.82 65	73.83 53	91.61 88	82.26 179

TAPA-MVS	65.27 12	75.16 94	74.29 107	77.77 72	74.86 212	68.08 77	77.89 101	84.04 68	55.15 176	76.19 173	83.39 198	66.91 106	80.11 145	60.04 168	90.14 126	85.13 90
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_prior4						70.14 63	77.57 102

EPNet		69.10 180	67.32 205	74.46 107	68.33 294	61.27 138	77.56 103	63.57 297	60.95 122	56.62 353	82.75 212	51.53 240	81.24 119	54.36 217	90.20 123	80.88 202
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FE-MVS		68.29 193	66.96 212	72.26 160	74.16 226	54.24 193	77.55 104	73.42 215	57.65 152	72.66 220	84.91 179	32.02 349	81.49 115	48.43 262	81.85 248	81.04 195

RPSCF		75.76 85	74.37 105	79.93 40	74.81 213	77.53 16	77.53 105	79.30 149	59.44 133	78.88 126	89.80 80	71.26 69	73.09 238	57.45 185	80.89 260	89.17 31

CSCG		74.12 107	74.39 104	73.33 128	79.35 144	61.66 132	77.45 106	81.98 94	62.47 114	79.06 125	80.19 246	61.83 154	78.79 164	59.83 170	87.35 176	79.54 228

HQP-NCC					82.37 111		77.32 107		59.08 134	71.58 234

ACMP_Plane					82.37 111		77.32 107		59.08 134	71.58 234

HQP-MVS		75.24 93	75.01 99	75.94 93	82.37 111	58.80 167	77.32 107	84.12 65	59.08 134	71.58 234	85.96 168	58.09 197	85.30 53	67.38 102	89.16 147	83.73 135

DTE-MVSNet		80.35 48	82.89 35	72.74 148	89.84 7	37.34 337	77.16 110	81.81 97	80.45 3	90.92 3	92.95 7	74.57 47	86.12 29	63.65 134	94.68 31	94.76 6

PS-CasMVS		80.41 47	82.86 36	73.07 135	89.93 6	39.21 317	77.15 111	81.28 107	79.74 5	90.87 4	92.73 11	75.03 43	84.93 62	63.83 133	95.19 15	95.07 3

XVG-OURS-SEG-HR		79.62 52	79.99 55	78.49 64	86.46 46	74.79 29	77.15 111	85.39 34	66.73 66	80.39 114	88.85 103	74.43 50	78.33 177	74.73 46	85.79 200	82.35 175

PEN-MVS		80.46 46	82.91 34	73.11 133	89.83 8	39.02 320	77.06 113	82.61 86	80.04 4	90.60 6	92.85 9	74.93 44	85.21 57	63.15 141	95.15 17	95.09 2

CP-MVSNet		79.48 54	81.65 45	72.98 138	89.66 12	39.06 319	76.76 114	80.46 127	78.91 7	90.32 7	91.70 25	68.49 91	84.89 63	63.40 138	95.12 18	95.01 4

tt0805		76.12 83	78.43 68	69.20 201	81.32 126	41.37 302	76.72 115	77.64 179	63.78 99	82.06 90	87.88 123	79.78 11	79.05 158	64.33 126	92.40 77	87.17 60

SixPastTwentyTwo		75.77 84	76.34 85	74.06 116	81.69 122	54.84 188	76.47 116	75.49 200	64.10 95	87.73 17	92.24 17	50.45 247	81.30 118	67.41 98	91.46 92	86.04 73

APD_test1		75.04 97	75.38 98	74.02 117	69.89 275	70.15 62	76.46 117	79.71 140	65.50 75	82.99 80	88.60 109	66.94 105	72.35 249	59.77 171	88.54 158	79.56 225

FA-MVS(test-final)		71.27 151	71.06 161	71.92 163	73.96 228	52.32 206	76.45 118	76.12 193	59.07 137	74.04 204	86.18 159	52.18 235	79.43 154	59.75 172	81.76 250	84.03 126

TEST9					85.47 63	69.32 70	76.42 119	78.69 161	53.73 203	76.97 149	86.74 139	66.84 107	81.10 122

train_agg		76.38 80	76.55 83	75.86 95	85.47 63	69.32 70	76.42 119	78.69 161	54.00 198	76.97 149	86.74 139	66.60 113	81.10 122	72.50 66	91.56 90	77.15 258

Vis-MVSNet		74.85 104	74.56 102	75.72 96	81.63 123	64.64 110	76.35 121	79.06 152	62.85 110	73.33 212	88.41 112	62.54 147	79.59 152	63.94 132	82.92 238	82.94 160
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DeepPCF-MVS	71.07 5	78.48 65	77.14 79	82.52 16	84.39 83	77.04 21	76.35 121	84.05 67	56.66 162	80.27 115	85.31 175	68.56 90	87.03 10	67.39 100	91.26 95	83.50 138

XVG-OURS		79.51 53	79.82 56	78.58 63	86.11 56	74.96 28	76.33 123	84.95 43	66.89 63	82.75 85	88.99 99	66.82 108	78.37 175	74.80 44	90.76 117	82.40 174

test_8					85.09 69	67.89 79	76.26 124	78.66 163	54.00 198	76.89 153	86.72 141	66.60 113	80.89 132

testf1		75.66 87	76.57 81	72.95 139	67.07 310	67.62 81	76.10 125	80.68 121	64.95 87	86.58 33	90.94 40	71.20 70	71.68 259	60.46 161	91.13 101	79.56 225

APD_test2		75.66 87	76.57 81	72.95 139	67.07 310	67.62 81	76.10 125	80.68 121	64.95 87	86.58 33	90.94 40	71.20 70	71.68 259	60.46 161	91.13 101	79.56 225

CDPH-MVS		77.33 73	77.06 80	78.14 69	84.21 84	63.98 115	76.07 127	83.45 74	54.20 193	77.68 143	87.18 126	69.98 80	85.37 51	68.01 91	92.72 74	85.08 92

CNLPA		73.44 114	73.03 131	74.66 105	78.27 163	75.29 26	75.99 128	78.49 165	65.39 78	75.67 175	83.22 209	61.23 163	66.77 305	53.70 223	85.33 206	81.92 184

iter_conf_final		68.69 186	67.00 211	73.76 121	73.68 232	52.33 205	75.96 129	73.54 213	50.56 239	69.90 257	82.85 210	24.76 385	83.73 78	65.40 118	86.33 195	85.22 87

test_fmvsmconf0.01_n		73.91 108	73.64 118	74.71 104	69.79 280	66.25 93	75.90 130	79.90 138	46.03 276	76.48 167	85.02 178	67.96 99	73.97 231	74.47 49	87.22 181	83.90 129

UGNet		70.20 163	69.05 178	73.65 122	76.24 193	63.64 116	75.87 131	72.53 224	61.48 118	60.93 333	86.14 162	52.37 234	77.12 195	50.67 241	85.21 208	80.17 219
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
v10		75.69 86	76.20 87	74.16 114	74.44 222	48.69 234	75.84 132	82.93 81	59.02 138	85.92 41	89.17 93	58.56 191	82.74 96	70.73 73	89.14 150	91.05 15

test_prior2							75.57 133		58.92 139	76.53 166	86.78 137	67.83 100		69.81 78	92.76 73

PAPR		69.20 178	68.66 187	70.82 172	75.15 208	47.77 248	75.31 134	81.11 111	49.62 250	66.33 295	79.27 261	61.53 158	82.96 93	48.12 266	81.50 257	81.74 187

v8		75.07 96	75.64 94	73.35 127	73.42 235	47.46 253	75.20 135	81.45 103	60.05 128	85.64 45	89.26 88	58.08 199	81.80 111	69.71 81	87.97 167	90.79 19

tttt0517		69.46 174	67.79 200	74.46 107	75.34 204	52.72 202	75.05 136	63.27 299	54.69 183	78.87 127	84.37 185	26.63 376	81.15 120	63.95 130	87.93 168	89.51 25

TSAR-MVS + GP.		73.08 123	71.60 155	77.54 73	78.99 157	70.73 57	74.96 137	69.38 257	60.73 124	74.39 196	78.44 273	57.72 205	82.78 95	60.16 165	89.60 138	79.11 233

MAR-MVS		67.72 200	66.16 218	72.40 157	74.45 221	64.99 107	74.87 138	77.50 181	48.67 257	65.78 299	68.58 355	57.01 212	77.79 188	46.68 279	81.92 246	74.42 279
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
无先验							74.82 139	70.94 247	47.75 266				76.85 200	54.47 213		72.09 300

CANet		73.00 128	71.84 149	76.48 87	75.82 201	61.28 137	74.81 140	80.37 130	63.17 108	62.43 323	80.50 240	61.10 167	85.16 60	64.00 129	84.34 224	83.01 159

PVSNet_Blended_VisFu		70.04 164	68.88 181	73.53 126	82.71 108	63.62 117	74.81 140	81.95 95	48.53 258	67.16 292	79.18 264	51.42 241	78.38 174	54.39 216	79.72 276	78.60 238

MCST-MVS		73.42 115	73.34 124	73.63 124	81.28 127	59.17 161	74.80 142	83.13 78	45.50 279	72.84 218	83.78 194	65.15 128	80.99 126	64.54 123	89.09 153	80.73 207

原ACMM2							74.78 143

Anonymous20231211		75.54 89	77.19 78	70.59 175	77.67 174	45.70 271	74.73 144	80.19 133	68.80 53	82.95 81	92.91 8	66.26 116	76.76 201	58.41 181	92.77 72	89.30 27

Effi-MVS+		72.10 145	72.28 145	71.58 165	74.21 225	50.33 217	74.72 145	82.73 83	62.62 111	70.77 246	76.83 289	69.96 81	80.97 128	60.20 163	78.43 287	83.45 144

K. test v3		73.67 111	73.61 119	73.87 119	79.78 138	55.62 186	74.69 146	62.04 306	66.16 71	84.76 60	93.23 5	49.47 252	80.97 128	65.66 116	86.67 191	85.02 94

MG-MVS		70.47 161	71.34 159	67.85 224	79.26 147	40.42 312	74.67 147	75.15 204	58.41 142	68.74 277	88.14 121	56.08 219	83.69 80	59.90 169	81.71 254	79.43 230

test_fmvsmconf0.1_n		73.26 120	72.82 135	74.56 106	69.10 286	66.18 95	74.65 148	79.34 148	45.58 278	75.54 178	83.91 191	67.19 103	73.88 234	73.26 57	86.86 186	83.63 137

UniMVSNet_ETH3D		76.74 78	79.02 61	69.92 191	89.27 19	43.81 282	74.47 149	71.70 229	72.33 35	85.50 50	93.65 3	77.98 21	76.88 199	54.60 212	91.64 86	89.08 32

GeoE		73.14 121	73.77 116	71.26 170	78.09 166	52.64 203	74.32 150	79.56 145	56.32 165	76.35 171	83.36 202	70.76 74	77.96 185	63.32 139	81.84 249	83.18 153

DP-MVS Recon		73.57 113	72.69 137	76.23 91	82.85 106	63.39 118	74.32 150	82.96 80	57.75 148	70.35 250	81.98 221	64.34 135	84.41 73	49.69 248	89.95 130	80.89 201

ambc				70.10 187	77.74 172	50.21 219	74.28 152	77.93 177		79.26 123	88.29 116	54.11 227	79.77 148	64.43 124	91.10 103	80.30 216

test_fmvsmconf_n		72.91 132	72.40 143	74.46 107	68.62 290	66.12 96	74.21 153	78.80 158	45.64 277	74.62 192	83.25 206	66.80 111	73.86 235	72.97 60	86.66 192	83.39 145

nrg030		74.87 103	75.99 90	71.52 167	74.90 211	49.88 228	74.10 154	82.58 87	54.55 187	83.50 75	89.21 90	71.51 65	75.74 209	61.24 152	92.34 79	88.94 37

fmvsm_s_conf0.1_n_a		67.37 207	66.36 216	70.37 179	70.86 262	61.17 139	74.00 155	57.18 325	40.77 319	68.83 276	80.88 234	63.11 141	67.61 292	66.94 107	74.72 312	82.33 178

canonicalmvs		72.29 144	73.38 122	69.04 204	74.23 223	47.37 254	73.93 156	83.18 76	54.36 188	76.61 162	81.64 227	72.03 61	75.34 213	57.12 187	87.28 179	84.40 118

CANet_DTU		64.04 244	63.83 244	64.66 251	68.39 291	42.97 292	73.45 157	74.50 209	52.05 218	54.78 361	75.44 300	43.99 281	70.42 270	53.49 225	78.41 288	80.59 212

fmvsm_s_conf0.5_n_a		67.00 213	65.95 223	70.17 184	69.72 281	61.16 140	73.34 158	56.83 328	40.96 316	68.36 279	80.08 249	62.84 142	67.57 293	66.90 109	74.50 316	81.78 186

ETV-MVS		72.72 136	72.16 147	74.38 112	76.90 186	55.95 180	73.34 158	84.67 51	62.04 115	72.19 229	70.81 334	65.90 120	85.24 56	58.64 178	84.96 214	81.95 183

PCF-MVS	63.80 13	72.70 137	71.69 151	75.72 96	78.10 165	60.01 155	73.04 160	81.50 101	45.34 283	79.66 119	84.35 186	65.15 128	82.65 97	48.70 258	89.38 146	84.50 117
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs_mvg		75.26 92	76.18 88	72.52 153	72.87 249	49.47 229	72.94 161	84.71 50	59.49 132	80.90 109	88.81 104	70.07 79	79.71 149	67.40 99	88.39 159	88.40 46
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_fmvsmvis_n_1920		72.36 142	72.49 140	71.96 162	71.29 260	64.06 114	72.79 162	81.82 96	40.23 324	81.25 103	81.04 232	70.62 75	68.69 281	69.74 80	83.60 234	83.14 154

test_0402		78.17 69	79.48 59	74.24 113	83.50 91	59.15 162	72.52 163	74.60 208	75.34 15	88.69 13	91.81 22	75.06 42	82.37 101	65.10 119	88.68 157	81.20 191

EU-MVSNet		60.82 272	60.80 271	60.86 291	68.37 292	41.16 303	72.27 164	68.27 265	26.96 379	69.08 266	75.71 295	32.09 346	67.44 294	55.59 203	78.90 282	73.97 281

EI-MVSNet-Vis-set		72.78 135	71.87 148	75.54 99	74.77 214	59.02 165	72.24 165	71.56 232	63.92 96	78.59 128	71.59 330	66.22 117	78.60 166	67.58 95	80.32 267	89.00 35

v1192		73.40 116	73.42 120	73.32 129	74.65 219	48.67 235	72.21 166	81.73 98	52.76 211	81.85 92	84.56 182	57.12 209	82.24 105	68.58 84	87.33 177	89.06 33

iter_conf05		67.34 208	65.62 224	72.50 154	69.82 276	47.06 258	72.19 167	76.86 187	45.32 284	72.86 217	82.85 210	20.53 392	83.73 78	61.13 155	89.02 154	86.70 65

fmvsm_s_conf0.1_n		66.60 215	65.54 225	69.77 192	68.99 287	59.15 162	72.12 168	56.74 330	40.72 321	68.25 282	80.14 248	61.18 166	66.92 299	67.34 104	74.40 317	83.23 152

baseline		73.10 122	73.96 112	70.51 177	71.46 258	46.39 265	72.08 169	84.40 58	55.95 169	76.62 161	86.46 152	67.20 102	78.03 184	64.22 127	87.27 180	87.11 61

EI-MVSNet-UG-set		72.63 138	71.68 152	75.47 100	74.67 216	58.64 170	72.02 170	71.50 233	63.53 102	78.58 130	71.39 333	65.98 118	78.53 167	67.30 105	80.18 269	89.23 29

v1144		73.29 119	73.39 121	73.01 136	74.12 227	48.11 241	72.01 171	81.08 114	53.83 202	81.77 94	84.68 180	58.07 200	81.91 109	68.10 88	86.86 186	88.99 36

dcpmvs_2		71.02 155	72.65 138	66.16 242	76.06 199	50.49 215	71.97 172	79.36 147	50.34 241	82.81 84	83.63 195	64.38 134	67.27 296	61.54 150	83.71 232	80.71 209

GBi-Net		68.30 191	68.79 182	66.81 235	73.14 240	40.68 308	71.96 173	73.03 216	54.81 178	74.72 188	90.36 67	48.63 261	75.20 215	47.12 273	85.37 203	84.54 112

test1		68.30 191	68.79 182	66.81 235	73.14 240	40.68 308	71.96 173	73.03 216	54.81 178	74.72 188	90.36 67	48.63 261	75.20 215	47.12 273	85.37 203	84.54 112

FMVSNet1		71.06 153	72.48 141	66.81 235	77.65 175	40.68 308	71.96 173	73.03 216	61.14 120	79.45 122	90.36 67	60.44 173	75.20 215	50.20 245	88.05 164	84.54 112

v1921920		72.96 131	72.98 132	72.89 144	74.67 216	47.58 251	71.92 176	80.69 120	51.70 223	81.69 98	83.89 192	56.58 215	82.25 104	68.34 86	87.36 175	88.82 40

v144192		72.99 129	73.06 130	72.77 146	74.58 220	47.48 252	71.90 177	80.44 128	51.57 224	81.46 100	84.11 189	58.04 201	82.12 106	67.98 92	87.47 173	88.70 43

v1240		73.06 125	73.14 127	72.84 145	74.74 215	47.27 256	71.88 178	81.11 111	51.80 221	82.28 89	84.21 187	56.22 218	82.34 102	68.82 83	87.17 184	88.91 38

FC-MVSNet-test		73.32 118	74.78 101	68.93 209	79.21 149	36.57 339	71.82 179	79.54 146	57.63 153	82.57 87	90.38 64	59.38 184	78.99 160	57.91 184	94.56 34	91.23 14

fmvsm_s_conf0.5_n		66.34 220	65.27 228	69.57 195	68.20 295	59.14 164	71.66 180	56.48 331	40.92 317	67.78 284	79.46 257	61.23 163	66.90 300	67.39 100	74.32 320	82.66 169

IterMVS-LS		73.01 127	73.12 129	72.66 150	73.79 231	49.90 224	71.63 181	78.44 166	58.22 143	80.51 112	86.63 146	58.15 195	79.62 150	62.51 143	88.20 161	88.48 44
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EG-PatchMatch MVS		70.70 158	70.88 163	70.16 185	82.64 110	58.80 167	71.48 182	73.64 212	54.98 177	76.55 164	81.77 224	61.10 167	78.94 161	54.87 208	80.84 262	72.74 293

LF4IMVS		67.50 202	67.31 206	68.08 222	58.86 362	61.93 128	71.43 183	75.90 197	44.67 289	72.42 224	80.20 245	57.16 207	70.44 269	58.99 177	86.12 197	71.88 301

v2v482		72.55 141	72.58 139	72.43 156	72.92 248	46.72 260	71.41 184	79.13 151	55.27 174	81.17 104	85.25 176	55.41 220	81.13 121	67.25 106	85.46 202	89.43 26

Fast-Effi-MVS+-dtu		70.00 165	68.74 185	73.77 120	73.47 234	64.53 111	71.36 185	78.14 173	55.81 171	68.84 275	74.71 305	65.36 126	75.75 208	52.00 231	79.00 281	81.03 196

新几何2							71.33 186

EI-MVSNet		69.61 172	69.01 180	71.41 169	73.94 229	49.90 224	71.31 187	71.32 238	58.22 143	75.40 181	70.44 336	58.16 194	75.85 205	62.51 143	79.81 273	88.48 44

CVMVSNet		59.21 285	58.44 288	61.51 283	73.94 229	47.76 249	71.31 187	64.56 289	26.91 381	60.34 335	70.44 336	36.24 329	67.65 290	53.57 224	68.66 354	69.12 327

thisisatest0530		67.05 212	65.16 231	72.73 149	73.10 243	50.55 214	71.26 189	63.91 295	50.22 243	74.46 195	80.75 236	26.81 375	80.25 141	59.43 174	86.50 193	87.37 54

旧先验2							71.17 190		45.11 286	78.54 131			61.28 327	59.19 176

FIs		72.56 139	73.80 114	68.84 212	78.74 160	37.74 333	71.02 191	79.83 139	56.12 166	80.88 110	89.45 85	58.18 193	78.28 178	56.63 190	93.36 64	90.51 21

TranMVSNet+NR-MVSNet		76.13 82	77.66 74	71.56 166	84.61 78	42.57 296	70.98 192	78.29 170	68.67 56	83.04 78	89.26 88	72.99 58	80.75 133	55.58 204	95.47 10	91.35 13

casdiffmvs		73.06 125	73.84 113	70.72 173	71.32 259	46.71 261	70.93 193	84.26 61	55.62 172	77.46 145	87.10 127	67.09 104	77.81 187	63.95 130	86.83 188	87.64 51
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CR-MVSNet		58.96 286	58.49 287	60.36 294	66.37 313	48.24 239	70.93 193	56.40 333	32.87 362	61.35 327	86.66 143	33.19 338	63.22 320	48.50 261	70.17 346	69.62 322

RPMNet		65.77 223	65.08 237	67.84 225	66.37 313	48.24 239	70.93 193	86.27 19	54.66 184	61.35 327	86.77 138	33.29 337	85.67 47	55.93 198	70.17 346	69.62 322

LFMVS		67.06 211	67.89 197	64.56 252	78.02 167	38.25 328	70.81 196	59.60 313	65.18 83	71.06 244	86.56 149	43.85 282	75.22 214	46.35 280	89.63 137	80.21 218

fmvsm_l_conf0.5_n		67.48 203	66.88 214	69.28 200	67.41 305	62.04 127	70.69 197	69.85 254	39.46 327	69.59 261	81.09 231	58.15 195	68.73 280	67.51 97	78.16 292	77.07 262

DPM-MVS		69.98 166	69.22 177	72.26 160	82.69 109	58.82 166	70.53 198	81.23 109	47.79 265	64.16 309	80.21 244	51.32 242	83.12 90	60.14 166	84.95 215	74.83 276

h-mvs33		73.08 123	71.61 154	77.48 74	83.89 89	72.89 44	70.47 199	71.12 245	54.28 189	77.89 137	83.41 197	49.04 255	80.98 127	63.62 135	90.77 116	78.58 239

MVS_111021_LR		72.10 145	71.82 150	72.95 139	79.53 142	73.90 36	70.45 200	66.64 271	56.87 158	76.81 157	81.76 225	68.78 88	71.76 257	61.81 146	83.74 230	73.18 288

UniMVSNet (Re)		75.00 98	75.48 96	73.56 125	83.14 96	47.92 245	70.41 201	81.04 115	63.67 100	79.54 120	86.37 154	62.83 143	81.82 110	57.10 188	95.25 14	90.94 17

test_fmvsm_n_1920		69.63 170	68.45 188	73.16 131	70.56 268	65.86 98	70.26 202	78.35 167	37.69 338	74.29 197	78.89 269	61.10 167	68.10 287	65.87 115	79.07 280	85.53 83

TinyColmap		67.98 196	69.28 174	64.08 256	67.98 299	46.82 259	70.04 203	75.26 202	53.05 208	77.36 146	86.79 136	59.39 183	72.59 246	45.64 286	88.01 166	72.83 291

fmvsm_l_conf0.5_n_a		66.66 214	65.97 222	68.72 214	67.09 308	61.38 135	70.03 204	69.15 259	38.59 334	68.41 278	80.36 242	56.56 216	68.32 285	66.10 111	77.45 296	76.46 263

VDDNet		71.60 149	73.13 128	67.02 234	86.29 47	41.11 304	69.97 205	66.50 272	68.72 55	74.74 187	91.70 25	59.90 178	75.81 207	48.58 260	91.72 84	84.15 125

EPNet_dtu		58.93 287	58.52 286	60.16 296	67.91 300	47.70 250	69.97 205	58.02 317	49.73 248	47.28 382	73.02 322	38.14 317	62.34 322	36.57 343	85.99 199	70.43 315
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVS_Test		69.84 168	70.71 165	67.24 230	67.49 304	43.25 290	69.87 207	81.22 110	52.69 212	71.57 237	86.68 142	62.09 153	74.51 224	66.05 112	78.74 283	83.96 127

alignmvs		70.54 160	71.00 162	69.15 203	73.50 233	48.04 244	69.85 208	79.62 141	53.94 201	76.54 165	82.00 220	59.00 187	74.68 222	57.32 186	87.21 182	84.72 102

GG-mvs-BLEND				52.24 330	60.64 350	29.21 378	69.73 209	42.41 381		45.47 385	52.33 389	20.43 393	68.16 286	25.52 388	65.42 364	59.36 371

pmmvs-eth3d		64.41 240	63.27 251	67.82 226	75.81 202	60.18 154	69.49 210	62.05 305	38.81 333	74.13 200	82.23 219	43.76 283	68.65 282	42.53 302	80.63 266	74.63 277

DU-MVS		74.91 100	75.57 95	72.93 142	83.50 91	45.79 268	69.47 211	80.14 135	65.22 82	81.74 96	87.08 128	61.82 155	81.07 124	56.21 196	94.98 20	91.93 8

EIA-MVS		68.59 188	67.16 207	72.90 143	75.18 207	55.64 185	69.39 212	81.29 106	52.44 213	64.53 305	70.69 335	60.33 174	82.30 103	54.27 218	76.31 300	80.75 206

PAPM		61.79 265	60.37 274	66.05 243	76.09 196	41.87 299	69.30 213	76.79 190	40.64 322	53.80 366	79.62 256	44.38 279	82.92 94	29.64 374	73.11 327	73.36 287

UniMVSNet_NR-MVSNet		74.90 101	75.65 93	72.64 151	83.04 102	45.79 268	69.26 214	78.81 156	66.66 67	81.74 96	86.88 134	63.26 139	81.07 124	56.21 196	94.98 20	91.05 15

MVP-Stereo		61.56 267	59.22 280	68.58 216	79.28 146	60.44 152	69.20 215	71.57 231	43.58 298	56.42 354	78.37 274	39.57 310	76.46 204	34.86 354	60.16 377	68.86 329
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
hse-mvs2		72.32 143	70.66 166	77.31 79	83.10 101	71.77 47	69.19 216	71.45 235	54.28 189	77.89 137	78.26 275	49.04 255	79.23 155	63.62 135	89.13 151	80.92 200

AUN-MVS		70.22 162	67.88 198	77.22 80	82.96 105	71.61 48	69.08 217	71.39 236	49.17 253	71.70 232	78.07 280	37.62 323	79.21 156	61.81 146	89.15 149	80.82 203

gg-mvs-nofinetune		55.75 301	56.75 300	52.72 329	62.87 338	28.04 380	68.92 218	41.36 388	71.09 41	50.80 374	92.63 12	20.74 391	66.86 302	29.97 372	72.41 330	63.25 357

Baseline_NR-MVSNet		70.62 159	73.19 126	62.92 272	76.97 182	34.44 355	68.84 219	70.88 248	60.25 127	79.50 121	90.53 53	61.82 155	69.11 278	54.67 211	95.27 13	85.22 87

v148		69.38 177	69.39 173	69.36 197	69.14 285	44.56 277	68.83 220	72.70 222	54.79 181	78.59 128	84.12 188	54.69 222	76.74 202	59.40 175	82.20 243	86.79 63

FMVSNet2		67.48 203	68.21 193	65.29 247	73.14 240	38.94 321	68.81 221	71.21 244	54.81 178	76.73 159	86.48 151	48.63 261	74.60 223	47.98 268	86.11 198	82.35 175

MVS_111021_HR		72.98 130	72.97 133	72.99 137	80.82 130	65.47 100	68.81 221	72.77 221	57.67 150	75.76 174	82.38 218	71.01 72	77.17 194	61.38 151	86.15 196	76.32 264

Anonymous20240529		72.56 139	73.79 115	68.86 211	76.89 187	45.21 273	68.80 223	77.25 185	67.16 61	76.89 153	90.44 56	65.95 119	74.19 229	50.75 240	90.00 128	87.18 59

Anonymous20240521		63.55 246	66.07 220	55.99 316	66.18 318	44.04 281	68.77 224	68.80 260	46.99 270	72.57 221	85.84 170	39.87 307	50.22 350	53.40 228	92.23 81	73.71 285

CLD-MVS		72.88 133	72.36 144	74.43 110	77.03 179	54.30 192	68.77 224	83.43 75	52.12 216	76.79 158	74.44 308	69.54 85	83.91 75	55.88 199	93.25 66	85.09 91
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
1314		59.83 281	58.86 284	62.74 273	65.71 321	44.78 276	68.59 226	72.63 223	33.54 361	61.05 331	67.29 361	43.62 284	71.26 262	49.49 251	67.84 359	72.19 299

MVS		60.62 275	59.97 276	62.58 274	68.13 297	47.28 255	68.59 226	73.96 211	32.19 363	59.94 338	68.86 352	50.48 246	77.64 191	41.85 307	75.74 302	62.83 358

OpenMVS_ROB	54.93 17	63.23 251	63.28 250	63.07 268	69.81 277	45.34 272	68.52 228	67.14 268	43.74 296	70.61 248	79.22 262	47.90 265	72.66 242	48.75 257	73.84 324	71.21 309

PM-MVS		64.49 237	63.61 247	67.14 233	76.68 189	75.15 27	68.49 229	42.85 380	51.17 233	77.85 139	80.51 239	45.76 269	66.31 308	52.83 229	76.35 299	59.96 369

BH-untuned		69.39 176	69.46 172	69.18 202	77.96 169	56.88 176	68.47 230	77.53 180	56.77 160	77.79 140	79.63 255	60.30 175	80.20 144	46.04 283	80.65 264	70.47 314

testdata1							68.34 231		57.24 156

tpm2		56.12 299	54.64 313	60.55 293	66.24 316	36.01 343	68.14 232	56.77 329	33.60 360	58.25 346	75.52 299	30.25 364	74.33 227	33.27 361	69.76 350	71.32 306

c3_l		69.82 169	69.89 170	69.61 194	66.24 316	43.48 286	68.12 233	79.61 143	51.43 226	77.72 141	80.18 247	54.61 224	78.15 183	63.62 135	87.50 172	87.20 58

CMPMVS	48.73 20	61.54 268	60.89 269	63.52 263	61.08 347	51.55 208	68.07 234	68.00 266	33.88 356	65.87 297	81.25 229	37.91 320	67.71 289	49.32 253	82.60 241	71.31 307
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test222					87.30 37	69.15 73	67.85 235	59.59 314	41.06 314	73.05 216	85.72 172	48.03 264			80.65 264	66.92 337

VDD-MVS		70.81 157	71.44 158	68.91 210	79.07 155	46.51 262	67.82 236	70.83 249	61.23 119	74.07 202	88.69 106	59.86 179	75.62 210	51.11 237	90.28 122	84.61 107

ab-mvs		64.11 243	65.13 234	61.05 288	71.99 255	38.03 332	67.59 237	68.79 261	49.08 255	65.32 301	86.26 157	58.02 202	66.85 303	39.33 320	79.79 275	78.27 243

eth_miper_zixun_eth		69.42 175	68.73 186	71.50 168	67.99 298	46.42 263	67.58 238	78.81 156	50.72 237	78.13 135	80.34 243	50.15 249	80.34 139	60.18 164	84.65 218	87.74 50

CostFormer		57.35 296	56.14 304	60.97 289	63.76 335	38.43 325	67.50 239	60.22 311	37.14 342	59.12 343	76.34 292	32.78 341	71.99 254	39.12 323	69.27 351	72.47 295

Patchmtry		60.91 271	63.01 254	54.62 321	66.10 319	26.27 385	67.47 240	56.40 333	54.05 197	72.04 230	86.66 143	33.19 338	60.17 329	43.69 296	87.45 174	77.42 253

USDC		62.80 256	63.10 253	61.89 279	65.19 324	43.30 289	67.42 241	74.20 210	35.80 348	72.25 227	84.48 184	45.67 270	71.95 255	37.95 333	84.97 211	70.42 316

xiu_mvs_v1_base_debu		67.87 197	67.07 208	70.26 181	79.13 152	61.90 129	67.34 242	71.25 241	47.98 261	67.70 285	74.19 313	61.31 160	72.62 243	56.51 191	78.26 289	76.27 265

xiu_mvs_v1_base		67.87 197	67.07 208	70.26 181	79.13 152	61.90 129	67.34 242	71.25 241	47.98 261	67.70 285	74.19 313	61.31 160	72.62 243	56.51 191	78.26 289	76.27 265

xiu_mvs_v1_base_debi		67.87 197	67.07 208	70.26 181	79.13 152	61.90 129	67.34 242	71.25 241	47.98 261	67.70 285	74.19 313	61.31 160	72.62 243	56.51 191	78.26 289	76.27 265

test2506		61.23 269	60.85 270	62.38 276	78.80 158	27.88 381	67.33 245	37.42 393	54.23 191	67.55 288	88.68 107	17.87 397	74.39 226	46.33 281	89.41 143	84.86 97

Vis-MVSNet (Re-imp)		62.74 257	63.21 252	61.34 286	72.19 253	31.56 368	67.31 246	53.87 342	53.60 204	69.88 258	83.37 200	40.52 303	70.98 264	41.40 310	86.78 189	81.48 190

jason		64.47 238	62.84 255	69.34 199	76.91 184	59.20 158	67.15 247	65.67 277	35.29 349	65.16 302	76.74 290	44.67 277	70.68 265	54.74 210	79.28 279	78.14 246
jason: jason.
miper_ehance_all_eth		68.36 190	68.16 195	68.98 206	65.14 327	43.34 288	67.07 248	78.92 155	49.11 254	76.21 172	77.72 282	53.48 229	77.92 186	61.16 154	84.59 220	85.68 82

pmmvs6		71.82 147	73.66 117	66.31 241	75.94 200	42.01 298	66.99 249	72.53 224	63.45 104	76.43 169	92.78 10	72.95 59	69.69 274	51.41 235	90.46 120	87.22 56

ECVR-MVS		64.82 231	65.22 229	63.60 261	78.80 158	31.14 371	66.97 250	56.47 332	54.23 191	69.94 256	88.68 107	37.23 324	74.81 221	45.28 291	89.41 143	84.86 97

PatchmatchNet		54.60 308	54.27 314	55.59 317	65.17 326	39.08 318	66.92 251	51.80 354	39.89 325	58.39 344	73.12 321	31.69 352	58.33 335	43.01 301	58.38 383	69.38 325
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MSDG		67.47 205	67.48 204	67.46 228	70.70 265	54.69 190	66.90 252	78.17 171	60.88 123	70.41 249	74.76 303	61.22 165	73.18 237	47.38 272	76.87 297	74.49 278

cl22		67.14 209	66.51 215	69.03 205	63.20 337	43.46 287	66.88 253	76.25 192	49.22 252	74.48 194	77.88 281	45.49 272	77.40 193	60.64 160	84.59 220	86.24 69

TAMVS		65.31 226	63.75 245	69.97 190	82.23 115	59.76 157	66.78 254	63.37 298	45.20 285	69.79 259	79.37 260	47.42 267	72.17 250	34.48 355	85.15 210	77.99 250

test_post1							66.63 255				2.08 398	30.66 362	59.33 331	40.34 317

FMVSNet3		65.00 230	65.16 231	64.52 253	69.47 282	37.56 336	66.63 255	70.38 251	51.55 225	74.72 188	83.27 205	37.89 321	74.44 225	47.12 273	85.37 203	81.57 189

mvs_anonymous		65.08 229	65.49 226	63.83 259	63.79 334	37.60 335	66.52 257	69.82 255	43.44 299	73.46 210	86.08 165	58.79 190	71.75 258	51.90 232	75.63 304	82.15 180

wuyk23d		61.97 262	66.25 217	49.12 346	58.19 366	60.77 150	66.32 258	52.97 350	55.93 170	90.62 5	86.91 133	73.07 57	35.98 391	20.63 395	91.63 87	50.62 381

tpm cat1		54.02 313	52.63 322	58.19 307	64.85 330	39.86 315	66.26 259	57.28 322	32.16 364	56.90 351	70.39 338	32.75 342	65.30 310	34.29 356	58.79 380	69.41 324

Fast-Effi-MVS+		68.81 183	68.30 190	70.35 180	74.66 218	48.61 236	66.06 260	78.32 168	50.62 238	71.48 240	75.54 297	68.75 89	79.59 152	50.55 243	78.73 284	82.86 163

V42		71.06 153	70.83 164	71.72 164	67.25 306	47.14 257	65.94 261	80.35 131	51.35 229	83.40 76	83.23 207	59.25 185	78.80 163	65.91 114	80.81 263	89.23 29

cl____		68.26 195	68.26 191	68.29 219	64.98 328	43.67 284	65.89 262	74.67 206	50.04 246	76.86 155	82.42 217	48.74 259	75.38 211	60.92 158	89.81 133	85.80 80

DIV-MVS_self_test		68.27 194	68.26 191	68.29 219	64.98 328	43.67 284	65.89 262	74.67 206	50.04 246	76.86 155	82.43 216	48.74 259	75.38 211	60.94 157	89.81 133	85.81 76

tpmvs		55.84 300	55.45 310	57.01 312	60.33 351	33.20 362	65.89 262	59.29 315	47.52 268	56.04 355	73.60 316	31.05 359	68.06 288	40.64 315	64.64 365	69.77 320

lupinMVS		63.36 248	61.49 264	68.97 207	74.93 209	59.19 159	65.80 265	64.52 290	34.68 354	63.53 319	74.25 311	43.19 286	70.62 266	53.88 222	78.67 285	77.10 259

TransMVSNet (Re)		69.62 171	71.63 153	63.57 262	76.51 190	35.93 345	65.75 266	71.29 240	61.05 121	75.02 183	89.90 79	65.88 121	70.41 271	49.79 247	89.48 141	84.38 119

NR-MVSNet		73.62 112	74.05 110	72.33 159	83.50 91	43.71 283	65.65 267	77.32 183	64.32 93	75.59 176	87.08 128	62.45 148	81.34 116	54.90 207	95.63 8	91.93 8

BH-w/o		64.81 232	64.29 240	66.36 240	76.08 198	54.71 189	65.61 268	75.23 203	50.10 245	71.05 245	71.86 329	54.33 225	79.02 159	38.20 331	76.14 301	65.36 347

PVSNet_BlendedMVS		65.38 225	64.30 239	68.61 215	69.81 277	49.36 230	65.60 269	78.96 153	45.50 279	59.98 336	78.61 271	51.82 237	78.20 180	44.30 292	84.11 226	78.27 243

test1111		64.62 234	65.19 230	62.93 271	79.01 156	29.91 375	65.45 270	54.41 341	54.09 196	71.47 241	88.48 111	37.02 325	74.29 228	46.83 278	89.94 131	84.58 110

thres100view900		61.17 270	61.09 267	61.39 285	72.14 254	35.01 351	65.42 271	56.99 326	55.23 175	70.71 247	79.90 251	32.07 347	72.09 251	35.61 350	81.73 251	77.08 260

CDS-MVSNet		64.33 241	62.66 257	69.35 198	80.44 134	58.28 171	65.26 272	65.66 278	44.36 290	67.30 291	75.54 297	43.27 285	71.77 256	37.68 334	84.44 223	78.01 249
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SCA		58.57 290	58.04 291	60.17 295	70.17 273	41.07 305	65.19 273	53.38 348	43.34 302	61.00 332	73.48 317	45.20 273	69.38 276	40.34 317	70.31 345	70.05 317

HY-MVS	49.31 19	57.96 293	57.59 294	59.10 302	66.85 312	36.17 342	65.13 274	65.39 282	39.24 330	54.69 363	78.14 278	44.28 280	67.18 298	33.75 360	70.79 341	73.95 282

ET-MVSNet_ETH3D		63.32 249	60.69 272	71.20 171	70.15 274	55.66 184	65.02 275	64.32 291	43.28 303	68.99 268	72.05 328	25.46 382	78.19 182	54.16 220	82.80 239	79.74 224

diffmvs		67.42 206	67.50 203	67.20 231	62.26 341	45.21 273	64.87 276	77.04 186	48.21 259	71.74 231	79.70 254	58.40 192	71.17 263	64.99 120	80.27 268	85.22 87
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
miper_enhance_ethall		65.86 222	65.05 238	68.28 221	61.62 345	42.62 295	64.74 277	77.97 175	42.52 304	73.42 211	72.79 323	49.66 250	77.68 190	58.12 182	84.59 220	84.54 112

thres600view7		61.82 264	61.38 265	63.12 267	71.81 256	34.93 352	64.64 278	56.99 326	54.78 182	70.33 251	79.74 253	32.07 347	72.42 248	38.61 327	83.46 235	82.02 181

BH-RMVSNet		68.69 186	68.20 194	70.14 186	76.40 191	53.90 197	64.62 279	73.48 214	58.01 145	73.91 206	81.78 223	59.09 186	78.22 179	48.59 259	77.96 293	78.31 242

pm-mvs1		68.40 189	69.85 171	64.04 258	73.10 243	39.94 314	64.61 280	70.50 250	55.52 173	73.97 205	89.33 86	63.91 137	68.38 284	49.68 249	88.02 165	83.81 131

pmmvs4		60.78 273	59.04 282	66.00 244	73.06 245	57.67 174	64.53 281	60.22 311	36.91 343	65.96 296	77.27 286	39.66 309	68.54 283	38.87 324	74.89 311	71.80 302

WR-MVS		71.20 152	72.48 141	67.36 229	84.98 71	35.70 347	64.43 282	68.66 262	65.05 86	81.49 99	86.43 153	57.57 206	76.48 203	50.36 244	93.32 65	89.90 23

tpmrst		50.15 334	51.38 329	46.45 356	56.05 373	24.77 388	64.40 283	49.98 358	36.14 345	53.32 367	69.59 345	35.16 331	48.69 355	39.24 321	58.51 382	65.89 343

VPA-MVSNet		68.71 185	70.37 167	63.72 260	76.13 195	38.06 331	64.10 284	71.48 234	56.60 164	74.10 201	88.31 115	64.78 132	69.72 273	47.69 271	90.15 125	83.37 147

MIMVSNet1		66.57 216	69.23 176	58.59 305	81.26 128	37.73 334	64.06 285	57.62 318	57.02 157	78.40 132	90.75 46	62.65 144	58.10 338	41.77 308	89.58 140	79.95 220

IterMVS		63.12 252	62.48 258	65.02 250	66.34 315	52.86 201	63.81 286	62.25 301	46.57 273	71.51 239	80.40 241	44.60 278	66.82 304	51.38 236	75.47 306	75.38 272
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		67.68 201	66.07 220	72.49 155	73.34 237	58.20 172	63.80 287	65.55 280	48.10 260	76.91 152	82.64 215	45.20 273	78.84 162	61.20 153	77.89 294	80.44 215

DELS-MVS		68.83 182	68.31 189	70.38 178	70.55 270	48.31 237	63.78 288	82.13 90	54.00 198	68.96 269	75.17 301	58.95 188	80.06 146	58.55 179	82.74 240	82.76 165
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
xiu_mvs_v2_base		64.43 239	63.96 243	65.85 246	77.72 173	51.32 210	63.63 289	72.31 227	45.06 288	61.70 324	69.66 344	62.56 145	73.93 233	49.06 255	73.91 322	72.31 297

tfpnnormal		66.48 217	67.93 196	62.16 278	73.40 236	36.65 338	63.45 290	64.99 284	55.97 168	72.82 219	87.80 124	57.06 211	69.10 279	48.31 264	87.54 170	80.72 208

TR-MVS		64.59 235	63.54 248	67.73 227	75.75 203	50.83 213	63.39 291	70.29 252	49.33 251	71.55 238	74.55 306	50.94 243	78.46 170	40.43 316	75.69 303	73.89 283

PS-MVSNAJ		64.27 242	63.73 246	65.90 245	77.82 171	51.42 209	63.33 292	72.33 226	45.09 287	61.60 325	68.04 356	62.39 149	73.95 232	49.07 254	73.87 323	72.34 296

tfpn200view9		60.35 277	59.97 276	61.51 283	70.78 263	35.35 349	63.27 293	57.47 319	53.00 209	68.31 280	77.09 287	32.45 344	72.09 251	35.61 350	81.73 251	77.08 260

thres400		60.77 274	59.97 276	63.15 266	70.78 263	35.35 349	63.27 293	57.47 319	53.00 209	68.31 280	77.09 287	32.45 344	72.09 251	35.61 350	81.73 251	82.02 181

test_yl		65.11 227	65.09 235	65.18 248	70.59 266	40.86 306	63.22 295	72.79 219	57.91 146	68.88 273	79.07 267	42.85 289	74.89 219	45.50 288	84.97 211	79.81 221

DCV-MVSNet		65.11 227	65.09 235	65.18 248	70.59 266	40.86 306	63.22 295	72.79 219	57.91 146	68.88 273	79.07 267	42.85 289	74.89 219	45.50 288	84.97 211	79.81 221

baseline1		57.82 294	58.36 290	56.19 315	69.17 284	30.76 373	62.94 297	55.21 336	46.04 275	63.83 314	78.47 272	41.20 297	63.68 317	39.44 319	68.99 352	74.13 280

baseline2		55.57 304	52.74 321	64.05 257	65.26 323	44.11 280	62.38 298	54.43 340	39.03 331	51.21 372	67.35 360	33.66 336	72.45 247	37.14 339	64.22 367	75.60 268

FPMVS		59.43 284	60.07 275	57.51 311	77.62 176	71.52 49	62.33 299	50.92 355	57.40 155	69.40 263	80.00 250	39.14 313	61.92 325	37.47 337	66.36 362	39.09 392

PatchMatch-RL		58.68 289	57.72 293	61.57 282	76.21 194	73.59 39	61.83 300	49.00 362	47.30 269	61.08 329	68.97 349	50.16 248	59.01 332	36.06 349	68.84 353	52.10 379

cascas		64.59 235	62.77 256	70.05 188	75.27 205	50.02 221	61.79 301	71.61 230	42.46 305	63.68 316	68.89 351	49.33 254	80.35 138	47.82 270	84.05 227	79.78 223

LCM-MVSNet-Re		69.10 180	71.57 156	61.70 281	70.37 271	34.30 357	61.45 302	79.62 141	56.81 159	89.59 8	88.16 120	68.44 92	72.94 239	42.30 303	87.33 177	77.85 252

1112_ss		59.48 283	58.99 283	60.96 290	77.84 170	42.39 297	61.42 303	68.45 264	37.96 337	59.93 339	67.46 358	45.11 275	65.07 311	40.89 314	71.81 336	75.41 271

IB-MVS	49.67 18	59.69 282	56.96 298	67.90 223	68.19 296	50.30 218	61.42 303	65.18 283	47.57 267	55.83 357	67.15 362	23.77 388	79.60 151	43.56 298	79.97 271	73.79 284
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
PVSNet_Blended		62.90 255	61.64 261	66.69 238	69.81 277	49.36 230	61.23 305	78.96 153	42.04 306	59.98 336	68.86 352	51.82 237	78.20 180	44.30 292	77.77 295	72.52 294

GA-MVS		62.91 254	61.66 260	66.66 239	67.09 308	44.49 278	61.18 306	69.36 258	51.33 230	69.33 264	74.47 307	36.83 326	74.94 218	50.60 242	74.72 312	80.57 213

MS-PatchMatch		55.59 303	54.89 312	57.68 310	69.18 283	49.05 233	61.00 307	62.93 300	35.98 346	58.36 345	68.93 350	36.71 327	66.59 306	37.62 336	63.30 369	57.39 375

patch_mono-2		62.73 258	64.08 242	58.68 304	70.36 272	55.87 182	60.84 308	64.11 294	41.23 312	64.04 310	78.22 276	60.00 176	48.80 354	54.17 219	83.71 232	71.37 305

testing3		58.28 291	58.38 289	58.00 309	77.45 177	26.12 386	60.78 309	43.00 379	56.02 167	70.18 253	75.76 294	13.27 404	67.24 297	48.02 267	80.89 260	80.65 210

MVSTER		63.29 250	61.60 263	68.36 217	59.77 358	46.21 266	60.62 310	71.32 238	41.83 307	75.40 181	79.12 265	30.25 364	75.85 205	56.30 195	79.81 273	83.03 158

thisisatest0515		60.48 276	57.86 292	68.34 218	67.25 306	46.42 263	60.58 311	62.14 302	40.82 318	63.58 318	69.12 347	26.28 378	78.34 176	48.83 256	82.13 244	80.26 217

tpm		50.60 331	52.42 324	45.14 361	65.18 325	26.29 384	60.30 312	43.50 376	37.41 340	57.01 350	79.09 266	30.20 366	42.32 380	32.77 363	66.36 362	66.81 340

VPNet		65.58 224	67.56 201	59.65 298	79.72 139	30.17 374	60.27 313	62.14 302	54.19 194	71.24 242	86.63 146	58.80 189	67.62 291	44.17 295	90.87 113	81.18 192

MIMVSNet		54.39 309	56.12 305	49.20 344	72.57 250	30.91 372	59.98 314	48.43 364	41.66 308	55.94 356	83.86 193	41.19 298	50.42 349	26.05 384	75.38 308	66.27 342

HyFIR lowres test		63.01 253	60.47 273	70.61 174	83.04 102	54.10 194	59.93 315	72.24 228	33.67 359	69.00 267	75.63 296	38.69 315	76.93 197	36.60 342	75.45 307	80.81 205

Patchmatch-RL test		59.95 280	59.12 281	62.44 275	72.46 251	54.61 191	59.63 316	47.51 367	41.05 315	74.58 193	74.30 310	31.06 358	65.31 309	51.61 233	79.85 272	67.39 334

PatchT		53.35 315	56.47 302	43.99 366	64.19 332	17.46 397	59.15 317	43.10 378	52.11 217	54.74 362	86.95 132	29.97 367	49.98 351	43.62 297	74.40 317	64.53 355

JIA-IIPM		54.03 312	51.62 326	61.25 287	59.14 361	55.21 187	59.10 318	47.72 365	50.85 235	50.31 378	85.81 171	20.10 394	63.97 315	36.16 347	55.41 388	64.55 354

Anonymous202405211		66.02 221	66.89 213	63.43 265	74.22 224	38.14 329	59.00 319	66.13 274	63.33 107	69.76 260	85.95 169	51.88 236	70.50 268	44.23 294	87.52 171	81.64 188

MDTV_nov1_ep13			54.05 316		65.54 322	29.30 377	59.00 319	55.22 335	35.96 347	52.44 368	75.98 293	30.77 361	59.62 330	38.21 330	73.33 326

thres200		57.55 295	57.02 297	59.17 300	67.89 301	34.93 352	58.91 321	57.25 323	50.24 242	64.01 311	71.46 332	32.49 343	71.39 261	31.31 366	79.57 277	71.19 310

test_fmvs3		56.78 297	55.99 306	59.12 301	53.96 385	48.09 242	58.76 322	66.22 273	27.54 377	76.66 160	68.69 354	25.32 384	51.31 347	53.42 227	73.38 325	77.97 251

SDMVSNet		66.36 219	67.85 199	61.88 280	73.04 246	46.14 267	58.54 323	71.36 237	51.42 227	68.93 271	82.72 213	65.62 122	62.22 324	54.41 215	84.67 216	77.28 255

dmvs_testset		45.26 347	47.51 345	38.49 375	59.96 355	14.71 399	58.50 324	43.39 377	41.30 311	51.79 371	56.48 384	39.44 311	49.91 353	21.42 393	55.35 389	50.85 380

ANet_high		67.08 210	69.94 169	58.51 306	57.55 367	27.09 382	58.43 325	76.80 189	63.56 101	82.40 88	91.93 20	59.82 180	64.98 312	50.10 246	88.86 156	83.46 143

ppachtmachnet_test		60.26 278	59.61 279	62.20 277	67.70 302	44.33 279	58.18 326	60.96 309	40.75 320	65.80 298	72.57 324	41.23 296	63.92 316	46.87 277	82.42 242	78.33 241

KD-MVS_self_test		66.38 218	67.51 202	62.97 270	61.76 343	34.39 356	58.11 327	75.30 201	50.84 236	77.12 148	85.42 173	56.84 213	69.44 275	51.07 238	91.16 98	85.08 92

Test_1112_low_res		58.78 288	58.69 285	59.04 303	79.41 143	38.13 330	57.62 328	66.98 270	34.74 352	59.62 342	77.56 284	42.92 288	63.65 318	38.66 326	70.73 342	75.35 273

VNet		64.01 245	65.15 233	60.57 292	73.28 238	35.61 348	57.60 329	67.08 269	54.61 185	66.76 294	83.37 200	56.28 217	66.87 301	42.19 304	85.20 209	79.23 232

sd_testset		63.55 246	65.38 227	58.07 308	73.04 246	38.83 323	57.41 330	65.44 281	51.42 227	68.93 271	82.72 213	63.76 138	58.11 337	41.05 312	84.67 216	77.28 255

DSMNet-mixed		43.18 356	44.66 356	38.75 374	54.75 380	28.88 379	57.06 331	27.42 399	13.47 395	47.27 383	77.67 283	38.83 314	39.29 388	25.32 389	60.12 378	48.08 383

test_vis1_n		51.27 329	50.41 339	53.83 322	56.99 369	50.01 222	56.75 332	60.53 310	25.68 383	59.74 341	57.86 383	29.40 369	47.41 361	43.10 300	63.66 368	64.08 356

test_fmvs2		54.80 307	54.11 315	56.88 313	51.76 389	49.95 223	56.70 333	65.80 276	26.22 382	69.42 262	65.25 365	31.82 350	49.98 351	49.63 250	70.36 344	70.71 313

CL-MVSNet_self_test		62.44 260	63.40 249	59.55 299	72.34 252	32.38 364	56.39 334	64.84 286	51.21 232	67.46 289	81.01 233	50.75 244	63.51 319	38.47 329	88.12 163	82.75 166

D2MVS		62.58 259	61.05 268	67.20 231	63.85 333	47.92 245	56.29 335	69.58 256	39.32 328	70.07 255	78.19 277	34.93 332	72.68 241	53.44 226	83.74 230	81.00 198

FMVSNet5		55.08 306	55.54 309	53.71 323	65.80 320	33.50 361	56.22 336	52.50 352	43.72 297	61.06 330	83.38 199	25.46 382	54.87 343	30.11 371	81.64 256	72.75 292

test_vis1_n_1920		52.96 316	53.50 317	51.32 334	59.15 360	44.90 275	56.13 337	64.29 292	30.56 373	59.87 340	60.68 378	40.16 305	47.47 360	48.25 265	62.46 371	61.58 366

MVS-HIRNet		45.53 346	47.29 346	40.24 372	62.29 340	26.82 383	56.02 338	37.41 394	29.74 374	43.69 392	81.27 228	33.96 334	55.48 341	24.46 390	56.79 384	38.43 393

test_fmvs1_n		52.70 318	52.01 325	54.76 319	53.83 386	50.36 216	55.80 339	65.90 275	24.96 385	65.39 300	60.64 379	27.69 373	48.46 356	45.88 285	67.99 357	65.46 346

pmmvs3		46.71 343	45.09 353	51.55 333	56.76 371	48.25 238	55.78 340	39.53 392	24.13 388	50.35 377	63.40 369	15.90 400	51.08 348	29.29 376	70.69 343	55.33 378

pmmvs5		52.49 321	52.58 323	52.21 331	54.99 379	32.38 364	55.45 341	53.84 343	32.15 365	55.49 359	74.81 302	38.08 318	57.37 340	34.02 357	74.40 317	66.88 338

our_test_3		56.46 298	56.51 301	56.30 314	67.70 302	39.66 316	55.36 342	52.34 353	40.57 323	63.85 313	69.91 343	40.04 306	58.22 336	43.49 299	75.29 310	71.03 312

Syy-MVS		54.13 310	55.45 310	50.18 338	68.77 288	23.59 390	55.02 343	44.55 374	43.80 293	58.05 347	64.07 367	46.22 268	58.83 333	46.16 282	72.36 331	68.12 330

myMVS_eth3d		50.36 333	50.52 338	49.88 339	68.77 288	22.69 392	55.02 343	44.55 374	43.80 293	58.05 347	64.07 367	14.16 403	58.83 333	33.90 359	72.36 331	68.12 330

EPMVS		45.74 345	46.53 348	43.39 367	54.14 383	22.33 394	55.02 343	35.00 396	34.69 353	51.09 373	70.20 340	25.92 380	42.04 382	37.19 338	55.50 387	65.78 344

dp		44.09 353	44.88 355	41.72 371	58.53 364	23.18 391	54.70 346	42.38 383	34.80 351	44.25 390	65.61 364	24.48 387	44.80 371	29.77 373	49.42 391	57.18 376

test_fmvs1		51.51 328	50.86 335	53.48 324	49.72 392	49.35 232	54.11 347	64.96 285	24.64 387	63.66 317	59.61 382	28.33 372	48.45 357	45.38 290	67.30 361	62.66 361

CHOSEN 1792x2688		58.09 292	56.30 303	63.45 264	79.95 137	50.93 212	54.07 348	65.59 279	28.56 375	61.53 326	74.33 309	41.09 299	66.52 307	33.91 358	67.69 360	72.92 290

MDTV_nov1_ep13_2view						18.41 396	53.74 349		31.57 369	44.89 387		29.90 368		32.93 362		71.48 304

SSC-MVS		61.79 265	66.08 219	48.89 348	76.91 184	10.00 402	53.56 350	47.37 368	68.20 58	76.56 163	89.21 90	54.13 226	57.59 339	54.75 209	74.07 321	79.08 234

dmvs_re		49.91 336	50.77 336	47.34 351	59.98 353	38.86 322	53.18 351	53.58 345	39.75 326	55.06 360	61.58 376	36.42 328	44.40 374	29.15 379	68.23 355	58.75 372

test-LLR		50.43 332	50.69 337	49.64 342	60.76 348	41.87 299	53.18 351	45.48 372	43.41 300	49.41 379	60.47 380	29.22 370	44.73 372	42.09 305	72.14 334	62.33 364

TESTMET0.1,1		45.17 348	44.93 354	45.89 358	56.02 374	38.31 326	53.18 351	41.94 386	27.85 376	44.86 388	56.47 385	17.93 396	41.50 384	38.08 332	68.06 356	57.85 373

test-mter		48.56 339	48.20 344	49.64 342	60.76 348	41.87 299	53.18 351	45.48 372	31.91 368	49.41 379	60.47 380	18.34 395	44.73 372	42.09 305	72.14 334	62.33 364

WB-MVS		60.04 279	64.19 241	47.59 350	76.09 196	10.22 401	52.44 355	46.74 369	65.17 84	74.07 202	87.48 125	53.48 229	55.28 342	49.36 252	72.84 328	77.28 255

Anonymous20231206		54.13 310	55.82 307	49.04 347	70.89 261	35.96 344	51.73 356	50.87 356	34.86 350	62.49 322	79.22 262	42.52 292	44.29 375	27.95 381	81.88 247	66.88 338

XXY-MVS		55.19 305	57.40 296	48.56 349	64.45 331	34.84 354	51.54 357	53.59 344	38.99 332	63.79 315	79.43 258	56.59 214	45.57 365	36.92 341	71.29 338	65.25 348

test_cas_vis1_n_1920		50.90 330	50.92 334	50.83 336	54.12 384	47.80 247	51.44 358	54.61 339	26.95 380	63.95 312	60.85 377	37.86 322	44.97 370	45.53 287	62.97 370	59.72 370

test20.03		55.74 302	57.51 295	50.42 337	59.89 357	32.09 366	50.63 359	49.01 361	50.11 244	65.07 303	83.23 207	45.61 271	48.11 359	30.22 370	83.82 229	71.07 311

UnsupCasMVSNet_eth		52.26 322	53.29 320	49.16 345	55.08 378	33.67 360	50.03 360	58.79 316	37.67 339	63.43 321	74.75 304	41.82 294	45.83 364	38.59 328	59.42 379	67.98 333

testgi		54.00 314	56.86 299	45.45 359	58.20 365	25.81 387	49.05 361	49.50 360	45.43 282	67.84 283	81.17 230	51.81 239	43.20 379	29.30 375	79.41 278	67.34 336

Patchmatch-test		47.93 340	49.96 341	41.84 369	57.42 368	24.26 389	48.75 362	41.49 387	39.30 329	56.79 352	73.48 317	30.48 363	33.87 392	29.29 376	72.61 329	67.39 334

UnsupCasMVSNet_bld		50.01 335	51.03 333	46.95 352	58.61 363	32.64 363	48.31 363	53.27 349	34.27 355	60.47 334	71.53 331	41.40 295	47.07 362	30.68 368	60.78 376	61.13 367

PVSNet	43.83 21	51.56 327	51.17 330	52.73 328	68.34 293	38.27 327	48.22 364	53.56 346	36.41 344	54.29 364	64.94 366	34.60 333	54.20 346	30.34 369	69.87 348	65.71 345

MDA-MVSNet-bldmvs		62.34 261	61.73 259	64.16 254	61.64 344	49.90 224	48.11 365	57.24 324	53.31 207	80.95 106	79.39 259	49.00 257	61.55 326	45.92 284	80.05 270	81.03 196

PMMVS		44.69 350	43.95 358	46.92 353	50.05 391	53.47 199	48.08 366	42.40 382	22.36 391	44.01 391	53.05 388	42.60 291	45.49 366	31.69 365	61.36 375	41.79 390

miper_lstm_enhance		61.97 262	61.63 262	62.98 269	60.04 352	45.74 270	47.53 367	70.95 246	44.04 291	73.06 215	78.84 270	39.72 308	60.33 328	55.82 200	84.64 219	82.88 161

ADS-MVSNet2		48.76 338	47.25 347	53.29 327	55.90 375	40.54 311	47.34 368	54.99 338	31.41 370	50.48 375	72.06 326	31.23 355	54.26 345	25.93 385	55.93 385	65.07 349

ADS-MVSNet		44.62 351	45.58 350	41.73 370	55.90 375	20.83 395	47.34 368	39.94 391	31.41 370	50.48 375	72.06 326	31.23 355	39.31 387	25.93 385	55.93 385	65.07 349

WTY-MVS		49.39 337	50.31 340	46.62 355	61.22 346	32.00 367	46.61 370	49.77 359	33.87 357	54.12 365	69.55 346	41.96 293	45.40 367	31.28 367	64.42 366	62.47 362

test0.0.03 1		47.72 341	48.31 343	45.93 357	55.53 377	29.39 376	46.40 371	41.21 389	43.41 300	55.81 358	67.65 357	29.22 370	43.77 378	25.73 387	69.87 348	64.62 353

test123		4.43 368	5.78 371	0.39 383	0.97 404	0.28 407	46.33 372	0.45 406	0.31 400	0.62 401	1.50 400	0.61 406	0.11 402	0.56 400	0.63 399	0.77 398

sss		47.59 342	48.32 342	45.40 360	56.73 372	33.96 358	45.17 373	48.51 363	32.11 367	52.37 369	65.79 363	40.39 304	41.91 383	31.85 364	61.97 373	60.35 368

KD-MVS_2432*1600		52.05 324	51.58 327	53.44 325	52.11 387	31.20 369	44.88 374	64.83 287	41.53 309	64.37 306	70.03 341	15.61 401	64.20 313	36.25 344	74.61 314	64.93 351

miper_refine_blended		52.05 324	51.58 327	53.44 325	52.11 387	31.20 369	44.88 374	64.83 287	41.53 309	64.37 306	70.03 341	15.61 401	64.20 313	36.25 344	74.61 314	64.93 351

test_vis3_rt		51.94 326	51.04 332	54.65 320	46.32 396	50.13 220	44.34 376	78.17 171	23.62 389	68.95 270	62.81 371	21.41 390	38.52 389	41.49 309	72.22 333	75.30 274

testmvs		4.06 369	5.28 372	0.41 382	0.64 405	0.16 408	42.54 377	0.31 407	0.26 401	0.50 402	1.40 401	0.77 405	0.17 401	0.56 400	0.55 400	0.90 397

mvsany_test3		43.76 355	41.01 359	52.01 332	48.09 394	57.74 173	42.47 378	23.85 402	23.30 390	64.80 304	62.17 374	27.12 374	40.59 385	29.17 378	48.11 392	57.69 374

PVSNet_0	36.71 22	41.12 358	40.78 361	42.14 368	59.97 354	40.13 313	40.97 379	42.24 385	30.81 372	44.86 388	49.41 392	40.70 302	45.12 369	23.15 391	34.96 395	41.16 391

YYNet1		52.58 319	53.50 317	49.85 340	54.15 382	36.45 341	40.53 380	46.55 371	38.09 336	75.52 179	73.31 320	41.08 300	43.88 376	41.10 311	71.14 340	69.21 326

MDA-MVSNet_test_wron		52.57 320	53.49 319	49.81 341	54.24 381	36.47 340	40.48 381	46.58 370	38.13 335	75.47 180	73.32 319	41.05 301	43.85 377	40.98 313	71.20 339	69.10 328

test_vis1_rt		46.70 344	45.24 352	51.06 335	44.58 397	51.04 211	39.91 382	67.56 267	21.84 393	51.94 370	50.79 391	33.83 335	39.77 386	35.25 353	61.50 374	62.38 363

new_pmnet		37.55 361	39.80 363	30.79 377	56.83 370	16.46 398	39.35 383	30.65 397	25.59 384	45.26 386	61.60 375	24.54 386	28.02 396	21.60 392	52.80 390	47.90 384

E-PMN		45.17 348	45.36 351	44.60 363	50.07 390	42.75 293	38.66 384	42.29 384	46.39 274	39.55 393	51.15 390	26.00 379	45.37 368	37.68 334	76.41 298	45.69 387

EMVS		44.61 352	44.45 357	45.10 362	48.91 393	43.00 291	37.92 385	41.10 390	46.75 272	38.00 395	48.43 393	26.42 377	46.27 363	37.11 340	75.38 308	46.03 386

N_pmnet		52.06 323	51.11 331	54.92 318	59.64 359	71.03 53	37.42 386	61.62 308	33.68 358	57.12 349	72.10 325	37.94 319	31.03 393	29.13 380	71.35 337	62.70 359

new-patchmatchnet		52.89 317	55.76 308	44.26 365	59.94 356	6.31 403	37.36 387	50.76 357	41.10 313	64.28 308	79.82 252	44.77 276	48.43 358	36.24 346	87.61 169	78.03 248

mvsany_test1		37.88 359	35.74 364	44.28 364	47.28 395	49.90 224	36.54 388	24.37 401	19.56 394	45.76 384	53.46 387	32.99 340	37.97 390	26.17 383	35.52 394	44.99 389

test_f		43.79 354	45.63 349	38.24 376	42.29 400	38.58 324	34.76 389	47.68 366	22.22 392	67.34 290	63.15 370	31.82 350	30.60 394	39.19 322	62.28 372	45.53 388

CHOSEN 280x420		41.62 357	39.89 362	46.80 354	61.81 342	51.59 207	33.56 390	35.74 395	27.48 378	37.64 396	53.53 386	23.24 389	42.09 381	27.39 382	58.64 381	46.72 385

PMMVS2		37.74 360	40.87 360	28.36 378	42.41 399	5.35 404	24.61 391	27.75 398	32.15 365	47.85 381	70.27 339	35.85 330	29.51 395	19.08 396	67.85 358	50.22 382

MVE	27.91 23	36.69 362	35.64 365	39.84 373	43.37 398	35.85 346	19.49 392	24.61 400	24.68 386	39.05 394	62.63 373	38.67 316	27.10 397	21.04 394	47.25 393	56.56 377
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		11.98 365	14.73 368	3.72 381	2.28 403	4.62 405	19.44 393	14.50 404	0.47 399	21.55 397	9.58 397	25.78 381	4.57 400	11.61 398	27.37 396	1.96 396

test_method		19.26 363	19.12 367	19.71 379	9.09 402	1.91 406	7.79 394	53.44 347	1.42 397	10.27 399	35.80 394	17.42 398	25.11 398	12.44 397	24.38 397	32.10 394

test_blank		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet_test		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

DCPMVS		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

cdsmvs_eth3d_5k		17.71 364	23.62 366	0.00 384	0.00 406	0.00 409	0.00 395	70.17 253	0.00 402	0.00 403	74.25 311	68.16 95	0.00 403	0.00 402	0.00 401	0.00 399

pcd_1.5k_mvsjas		5.20 367	6.93 370	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	62.39 149	0.00 403	0.00 402	0.00 401	0.00 399

sosnet-low-res		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uncertanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

Regformer		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

ab-mvs-re		5.62 366	7.50 369	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	67.46 358	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

WAC-MVS						22.69 392								36.10 348

MSC_two_6792asdad				79.02 55	83.14 96	67.03 87		80.75 118					86.24 22	77.27 33	94.85 25	83.78 132

PC_three_1452									46.98 271	81.83 93	86.28 155	66.55 115	84.47 71	63.31 140	90.78 114	83.49 139

No_MVS				79.02 55	83.14 96	67.03 87		80.75 118					86.24 22	77.27 33	94.85 25	83.78 132

test_one_0601					85.84 61	61.45 134		85.63 27	75.27 17	85.62 48	90.38 64	76.72 27

eth-test2					0.00 406

eth-test					0.00 406

ZD-MVS					83.91 87	69.36 69		81.09 113	58.91 140	82.73 86	89.11 95	75.77 35	86.63 12	72.73 62	92.93 70

IU-MVS					86.12 53	60.90 145		80.38 129	45.49 281	81.31 101				75.64 41	94.39 41	84.65 103

test_241102_TWO								84.80 44	72.61 30	84.93 56	89.70 81	77.73 22	85.89 40	75.29 42	94.22 52	83.25 150

test_241102_ONE					86.12 53	61.06 141		84.72 48	72.64 29	87.38 24	89.47 84	77.48 23	85.74 44

test_0728_THIRD									74.03 21	85.83 43	90.41 59	75.58 37	85.69 45	77.43 30	94.74 29	84.31 121

GSMVS																70.05 317

test_part2					85.90 57	66.44 91				84.61 62

sam_mvs1												31.41 353				70.05 317

sam_mvs												31.21 357

MTGPA								80.63 123

test_post											1.99 399	30.91 360	54.76 344

patchmatchnet-post											68.99 348	31.32 354	69.38 276

gm-plane-assit					62.51 339	33.91 359			37.25 341		62.71 372		72.74 240	38.70 325

test9_res														72.12 69	91.37 93	77.40 254

agg_prior2														70.70 75	90.93 108	78.55 240

agg_prior					84.44 82	66.02 97		78.62 164		76.95 151			80.34 139

TestCases				78.35 66	79.19 150	70.81 55		88.64 3	65.37 79	80.09 116	88.17 118	70.33 76	78.43 172	55.60 201	90.90 110	85.81 76

test_prior				75.27 102	82.15 116	59.85 156		84.33 59					83.39 86			82.58 171

新几何1				69.99 189	88.37 34	71.34 51		62.08 304	43.85 292	74.99 184	86.11 164	52.85 232	70.57 267	50.99 239	83.23 237	68.05 332

旧先验1					84.55 79	60.36 153		63.69 296			87.05 131	54.65 223			83.34 236	69.66 321

原ACMM1				73.90 118	85.90 57	65.15 106		81.67 99	50.97 234	74.25 198	86.16 161	61.60 157	83.54 82	56.75 189	91.08 104	73.00 289

testdata2													67.30 295	48.34 263

segment_acmp												68.30 94

testdata				64.13 255	85.87 59	63.34 119		61.80 307	47.83 264	76.42 170	86.60 148	48.83 258	62.31 323	54.46 214	81.26 258	66.74 341

test12				76.51 86	82.28 114	60.94 144		81.64 100		73.60 207		64.88 130	85.19 59		90.42 121	83.38 146

plane_prior7					85.18 66	66.21 94

plane_prior6					84.18 85	65.31 103						60.83 170

plane_prior5								85.49 29					86.15 27	71.09 71	90.94 106	84.82 99

plane_prior4											89.11 95

plane_prior3						65.67 99			63.82 98	78.23 133

plane_prior1					84.46 81

n2								0.00 408

nn								0.00 408

door-mid								55.02 337

lessismore_v0				72.75 147	79.60 141	56.83 178		57.37 321		83.80 72	89.01 98	47.45 266	78.74 165	64.39 125	86.49 194	82.69 168

LGP-MVS_train				80.90 32	87.00 39	70.41 60		86.35 16	69.77 50	87.75 15	91.13 34	81.83 3	86.20 24	77.13 35	95.96 5	86.08 71

test11								82.71 84

door								52.91 351

HQP5-MVS						58.80 167

BP-MVS														67.38 102

HQP4-MVS										71.59 233			85.31 52			83.74 134

HQP3-MVS								84.12 65							89.16 147

HQP2-MVS												58.09 197

NP-MVS					83.34 95	63.07 122					85.97 167

ACMMP++_ref															89.47 142

ACMMP++															91.96 83

Test By Simon												62.56 145

ITE_SJBPF				80.35 38	76.94 183	73.60 38		80.48 126	66.87 64	83.64 74	86.18 159	70.25 78	79.90 147	61.12 156	88.95 155	87.56 53

DeepMVS_CX				11.83 380	15.51 401	13.86 400		11.25 405	5.76 396	20.85 398	26.46 395	17.06 399	9.22 399	9.69 399	13.82 398	12.42 395

High-resolution multi-view benchmark