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.

MM		89.16 6	89.23 7	88.97 4	90.79 98	73.65 10	92.66 24	91.17 137	86.57 1	87.39 53	94.97 21	71.70 58	97.68 1	92.19 1	95.63 28	95.57 1

UA-Net		85.08 80	84.96 80	85.45 85	92.07 75	68.07 141	89.78 85	90.86 148	82.48 2	84.60 87	93.20 82	69.35 89	95.22 84	71.39 221	90.88 109	93.07 126

MGCNet		87.69 21	87.55 26	88.12 13	89.45 134	71.76 53	91.47 52	89.54 193	82.14 3	86.65 61	94.28 42	68.28 108	97.46 6	90.81 6	95.31 34	95.15 8

CANet		86.45 45	86.10 57	87.51 38	90.09 111	70.94 72	89.70 88	92.59 75	81.78 4	81.32 145	91.43 133	70.34 75	97.23 14	84.26 70	93.36 70	94.37 50

NCCC		88.06 15	88.01 19	88.24 11	94.41 22	73.62 11	91.22 57	92.83 61	81.50 5	85.79 67	93.47 75	73.02 42	97.00 18	84.90 59	94.94 40	94.10 64

EPNet		83.72 99	82.92 113	86.14 68	84.22 319	69.48 97	91.05 59	85.27 308	81.30 6	76.83 236	91.65 121	66.09 137	95.56 64	76.00 168	93.85 64	93.38 107
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 65	93.00 47	80.90 7	88.06 39	94.06 54	76.43 16	96.84 21	88.48 35	95.99 18	94.34 52

3Dnovator+	77.84 4	85.48 69	84.47 88	88.51 7	91.08 89	73.49 16	93.18 12	93.78 19	80.79 8	76.66 241	93.37 78	60.40 224	96.75 26	77.20 149	93.73 66	95.29 6

TranMVSNet+NR-MVSNet		80.84 164	80.31 161	82.42 226	87.85 208	62.33 293	87.74 175	91.33 132	80.55 9	77.99 210	89.86 177	65.23 146	92.62 213	67.05 268	75.24 362	92.30 163

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 17	94.11 7	80.27 10	91.35 14	94.16 49	78.35 13	96.77 24	89.59 17	94.22 62	94.67 30
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
HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 28	92.85 60	80.26 11	87.78 44	94.27 43	75.89 19	96.81 23	87.45 43	96.44 9	93.05 129

fmvsm_s_conf0.5_n_9		87.39 30	87.95 20	85.70 77	89.48 133	67.88 149	88.59 140	89.05 221	80.19 12	90.70 17	95.40 15	74.56 25	93.92 147	91.54 2	92.07 87	95.31 5

UniMVSNet_NR-MVSNet		81.88 140	81.54 139	82.92 205	88.46 180	63.46 268	87.13 193	92.37 82	80.19 12	78.38 199	89.14 202	71.66 60	93.05 199	70.05 236	76.46 335	92.25 165

SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 74	72.96 25	93.73 5	93.67 21	80.19 12	88.10 38	94.80 23	73.76 34	97.11 15	87.51 42	95.82 21	94.90 15
Skip Steuart: Steuart Systems R&D Blog.
EI-MVSNet-Vis-set		84.19 88	83.81 94	85.31 89	88.18 190	67.85 150	87.66 176	89.73 187	80.05 15	82.95 118	89.59 191	70.74 72	94.82 104	80.66 113	84.72 218	93.28 113

ETV-MVS		84.90 84	84.67 84	85.59 82	89.39 138	68.66 123	88.74 134	92.64 73	79.97 16	84.10 98	85.71 302	69.32 90	95.38 78	80.82 108	91.37 100	92.72 142

fmvsm_s_conf0.5_n_8		86.56 44	87.17 35	84.73 116	87.76 216	65.62 207	89.20 108	92.21 91	79.94 17	89.74 23	94.86 22	68.63 102	94.20 132	90.83 5	91.39 99	94.38 49

EI-MVSNet-UG-set		83.81 94	83.38 104	85.09 99	87.87 207	67.53 162	87.44 185	89.66 188	79.74 18	82.23 129	89.41 200	70.24 78	94.74 110	79.95 118	83.92 233	92.99 134

fmvsm_s_conf0.5_n_3		86.36 50	87.46 29	83.09 194	87.08 247	65.21 216	89.09 117	90.21 170	79.67 19	89.98 20	95.02 20	73.17 39	91.71 256	91.30 3	91.60 94	92.34 160

CS-MVS		86.69 41	86.95 39	85.90 74	90.76 99	67.57 160	92.83 18	93.30 33	79.67 19	84.57 88	92.27 102	71.47 61	95.02 96	84.24 72	93.46 69	95.13 9

casdiffmvs_mvg		85.99 55	86.09 58	85.70 77	87.65 221	67.22 175	88.69 136	93.04 42	79.64 21	85.33 71	92.54 99	73.30 36	94.50 120	83.49 78	91.14 103	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
MTAPA		87.23 33	87.00 36	87.90 22	94.18 35	74.25 5	86.58 218	92.02 99	79.45 22	85.88 65	94.80 23	68.07 110	96.21 46	86.69 48	95.34 32	93.23 114

EC-MVSNet		86.01 54	86.38 48	84.91 108	89.31 143	66.27 190	92.32 31	93.63 22	79.37 23	84.17 97	91.88 113	69.04 97	95.43 73	83.93 76	93.77 65	93.01 132

NormalMVS		86.29 51	85.88 61	87.52 37	93.26 52	72.47 38	91.65 43	92.19 93	79.31 24	84.39 91	92.18 104	64.64 152	95.53 67	80.70 111	94.65 48	94.56 41

SymmetryMVS		85.38 74	84.81 82	87.07 46	91.47 83	72.47 38	91.65 43	88.06 252	79.31 24	84.39 91	92.18 104	64.64 152	95.53 67	80.70 111	90.91 108	93.21 117

XVS		87.18 34	86.91 41	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 108	94.17 48	67.45 117	96.60 33	83.06 82	94.50 53	94.07 66

X-MVStestdata		80.37 187	77.83 227	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 108	12.47 469	67.45 117	96.60 33	83.06 82	94.50 53	94.07 66

HQP_MVS		83.64 102	83.14 107	85.14 94	90.08 112	68.71 119	91.25 55	92.44 78	79.12 28	78.92 186	91.00 150	60.42 222	95.38 78	78.71 131	86.32 189	91.33 198

plane_prior2							91.25 55		79.12 28

IS-MVSNet		83.15 117	82.81 114	84.18 141	89.94 119	63.30 272	91.59 46	88.46 245	79.04 30	79.49 175	92.16 106	65.10 147	94.28 126	67.71 259	91.86 92	94.95 12

DU-MVS		81.12 160	80.52 156	82.90 206	87.80 211	63.46 268	87.02 198	91.87 109	79.01 31	78.38 199	89.07 204	65.02 148	93.05 199	70.05 236	76.46 335	92.20 168

NR-MVSNet		80.23 191	79.38 188	82.78 216	87.80 211	63.34 271	86.31 227	91.09 141	79.01 31	72.17 330	89.07 204	67.20 120	92.81 211	66.08 275	75.65 348	92.20 168

SPE-MVS-test		86.29 51	86.48 47	85.71 76	91.02 91	67.21 176	92.36 30	93.78 19	78.97 33	83.51 111	91.20 140	70.65 74	95.15 87	81.96 97	94.89 42	94.77 25

DELS-MVS		85.41 72	85.30 76	85.77 75	88.49 178	67.93 148	85.52 254	93.44 28	78.70 34	83.63 110	89.03 206	74.57 24	95.71 62	80.26 116	94.04 63	93.66 90
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
WR-MVS		79.49 204	79.22 195	80.27 279	88.79 168	58.35 339	85.06 264	88.61 243	78.56 35	77.65 217	88.34 229	63.81 160	90.66 298	64.98 284	77.22 323	91.80 182

plane_prior3						68.60 124			78.44 36	78.92 186

UniMVSNet (Re)		81.60 148	81.11 144	83.09 194	88.38 184	64.41 242	87.60 177	93.02 46	78.42 37	78.56 194	88.16 235	69.78 83	93.26 181	69.58 243	76.49 334	91.60 188

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 61	95.06 1	94.23 3	78.38 38	92.78 4	95.74 6	82.45 3	97.49 4	89.42 19	96.68 2	94.95 12

test_0728_THIRD									78.38 38	92.12 9	95.78 4	81.46 7	97.40 9	89.42 19	96.57 7	94.67 30

testing3-2		75.12 304	75.19 286	74.91 365	90.40 105	45.09 448	80.29 355	78.42 400	78.37 40	76.54 246	87.75 245	44.36 381	87.28 352	57.04 358	83.49 245	92.37 159

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

SD-MVS		88.06 15	88.50 15	86.71 56	92.60 71	72.71 29	91.81 42	93.19 36	77.87 42	90.32 19	94.00 58	74.83 23	93.78 154	87.63 41	94.27 61	93.65 94
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
casdiffmvs		85.11 79	85.14 78	85.01 101	87.20 238	65.77 204	87.75 174	92.83 61	77.84 43	84.36 94	92.38 101	72.15 51	93.93 146	81.27 104	90.48 114	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
KinetiMVS		83.31 115	82.61 119	85.39 87	87.08 247	67.56 161	88.06 162	91.65 120	77.80 44	82.21 130	91.79 116	57.27 249	94.07 138	77.77 142	89.89 127	94.56 41

BP-MVS1		84.32 87	83.71 97	86.17 64	87.84 209	67.85 150	89.38 103	89.64 190	77.73 45	83.98 101	92.12 109	56.89 254	95.43 73	84.03 75	91.75 93	95.24 7

CP-MVSNet		78.22 239	78.34 213	77.84 330	87.83 210	54.54 396	87.94 167	91.17 137	77.65 46	73.48 312	88.49 225	62.24 185	88.43 337	62.19 307	74.07 371	90.55 229

plane_prior						68.71 119	90.38 73		77.62 47						86.16 194

baseline		84.93 82	84.98 79	84.80 113	87.30 236	65.39 213	87.30 190	92.88 58	77.62 47	84.04 100	92.26 103	71.81 55	93.96 140	81.31 102	90.30 117	95.03 11

VDD-MVS		83.01 122	82.36 124	84.96 103	91.02 91	66.40 187	88.91 122	88.11 248	77.57 49	84.39 91	93.29 80	52.19 295	93.91 148	77.05 152	88.70 149	94.57 39

MP-MVS		87.71 20	87.64 23	87.93 21	94.36 26	73.88 6	92.71 23	92.65 71	77.57 49	83.84 104	94.40 37	72.24 50	96.28 43	85.65 54	95.30 35	93.62 97
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PEN-MVS		77.73 254	77.69 235	77.84 330	87.07 249	53.91 401	87.91 169	91.18 136	77.56 51	73.14 316	88.82 215	61.23 206	89.17 323	59.95 327	72.37 386	90.43 234

OPM-MVS		83.50 107	82.95 112	85.14 94	88.79 168	70.95 71	89.13 115	91.52 126	77.55 52	80.96 153	91.75 117	60.71 214	94.50 120	79.67 122	86.51 187	89.97 261
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DeepPCF-MVS	80.84 1	88.10 13	88.56 14	86.73 55	92.24 73	69.03 106	89.57 93	93.39 31	77.53 53	89.79 21	94.12 51	78.98 12	96.58 35	85.66 53	95.72 24	94.58 37

PS-CasMVS		78.01 248	78.09 219	77.77 332	87.71 218	54.39 398	88.02 163	91.22 134	77.50 54	73.26 314	88.64 220	60.73 213	88.41 338	61.88 311	73.88 375	90.53 230

MSLP-MVS++		85.43 71	85.76 65	84.45 124	91.93 77	70.24 81	90.71 62	92.86 59	77.46 55	84.22 95	92.81 94	67.16 121	92.94 203	80.36 114	94.35 59	90.16 245

RRT-MVS		82.60 130	82.10 130	84.10 143	87.98 203	62.94 283	87.45 184	91.27 133	77.42 56	79.85 170	90.28 169	56.62 257	94.70 113	79.87 120	88.15 158	94.67 30

DVP-MVS		89.60 3	90.35 3	87.33 41	95.27 5	71.25 61	93.49 10	92.73 65	77.33 57	92.12 9	95.78 4	80.98 9	97.40 9	89.08 22	96.41 12	93.33 111
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					95.27 5	71.25 61	93.60 7	94.11 7	77.33 57	92.81 3	95.79 3	80.98 9

balanced_conf03		86.78 39	86.99 37	86.15 66	91.24 86	67.61 158	90.51 65	92.90 57	77.26 59	87.44 52	91.63 123	71.27 65	96.06 50	85.62 55	95.01 37	94.78 24

SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 68	93.57 8	94.06 11	77.24 60	93.10 1	95.72 8	82.99 1	97.44 7	89.07 24	96.63 4	94.88 16

test_241102_TWO								94.06 11	77.24 60	92.78 4	95.72 8	81.26 8	97.44 7	89.07 24	96.58 6	94.26 57

3Dnovator	76.31 5	83.38 111	82.31 125	86.59 57	87.94 204	72.94 28	90.64 63	92.14 98	77.21 62	75.47 267	92.83 92	58.56 236	94.72 111	73.24 200	92.71 77	92.13 175

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

WR-MVS_H		78.51 234	78.49 208	78.56 314	88.02 200	56.38 373	88.43 145	92.67 68	77.14 64	73.89 306	87.55 253	66.25 133	89.24 321	58.92 338	73.55 378	90.06 255

lecture		88.09 14	88.59 13	86.58 58	93.26 52	69.77 92	93.70 6	94.16 5	77.13 65	89.76 22	95.52 14	72.26 49	96.27 44	86.87 46	94.65 48	93.70 89

DeepC-MVS	79.81 2	87.08 37	86.88 42	87.69 33	91.16 87	72.32 45	90.31 74	93.94 15	77.12 66	82.82 122	94.23 46	72.13 52	97.09 16	84.83 62	95.37 31	93.65 94
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FC-MVSNet-test		81.52 152	82.02 133	80.03 284	88.42 183	55.97 379	87.95 166	93.42 30	77.10 67	77.38 222	90.98 152	69.96 81	91.79 251	68.46 255	84.50 221	92.33 161

DTE-MVSNet		76.99 270	76.80 255	77.54 338	86.24 268	53.06 410	87.52 179	90.66 152	77.08 68	72.50 324	88.67 219	60.48 221	89.52 315	57.33 355	70.74 398	90.05 256

LFMVS		81.82 142	81.23 142	83.57 175	91.89 78	63.43 270	89.84 81	81.85 361	77.04 69	83.21 113	93.10 83	52.26 294	93.43 174	71.98 216	89.95 125	93.85 78

UGNet		80.83 165	79.59 184	84.54 120	88.04 199	68.09 140	89.42 100	88.16 247	76.95 70	76.22 253	89.46 196	49.30 338	93.94 143	68.48 254	90.31 116	91.60 188
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
FIs		82.07 136	82.42 121	81.04 261	88.80 167	58.34 340	88.26 155	93.49 27	76.93 71	78.47 198	91.04 146	69.92 82	92.34 231	69.87 240	84.97 214	92.44 158

GST-MVS		87.42 28	87.26 31	87.89 24	94.12 36	72.97 24	92.39 27	93.43 29	76.89 72	84.68 81	93.99 60	70.67 73	96.82 22	84.18 74	95.01 37	93.90 76

mPP-MVS		86.67 43	86.32 49	87.72 30	94.41 22	73.55 13	92.74 21	92.22 89	76.87 73	82.81 123	94.25 45	66.44 130	96.24 45	82.88 87	94.28 60	93.38 107

ZNCC-MVS		87.94 19	87.85 21	88.20 12	94.39 24	73.33 19	93.03 15	93.81 18	76.81 74	85.24 72	94.32 40	71.76 56	96.93 19	85.53 56	95.79 22	94.32 54

VPNet		78.69 229	78.66 205	78.76 309	88.31 186	55.72 383	84.45 282	86.63 289	76.79 75	78.26 202	90.55 163	59.30 230	89.70 313	66.63 270	77.05 325	90.88 214

HFP-MVS		87.58 23	87.47 28	87.94 19	94.58 16	73.54 15	93.04 13	93.24 34	76.78 76	84.91 77	94.44 35	70.78 71	96.61 32	84.53 67	94.89 42	93.66 90

ACMMPR		87.44 26	87.23 33	88.08 15	94.64 13	73.59 12	93.04 13	93.20 35	76.78 76	84.66 84	94.52 28	68.81 99	96.65 30	84.53 67	94.90 41	94.00 70

ACMMP		85.89 61	85.39 72	87.38 40	93.59 45	72.63 33	92.74 21	93.18 40	76.78 76	80.73 159	93.82 67	64.33 154	96.29 42	82.67 94	90.69 111	93.23 114
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
region2R		87.42 28	87.20 34	88.09 14	94.63 14	73.55 13	93.03 15	93.12 41	76.73 79	84.45 89	94.52 28	69.09 93	96.70 27	84.37 69	94.83 45	94.03 68

sasdasda		85.91 59	85.87 63	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 41	91.23 137	73.28 37	93.91 148	81.50 100	88.80 145	94.77 25

canonicalmvs		85.91 59	85.87 63	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 41	91.23 137	73.28 37	93.91 148	81.50 100	88.80 145	94.77 25

CP-MVS		87.11 35	86.92 40	87.68 34	94.20 34	73.86 7	93.98 3	92.82 64	76.62 82	83.68 107	94.46 32	67.93 112	95.95 58	84.20 73	94.39 57	93.23 114

DeepC-MVS_fast	79.65 3	86.91 38	86.62 46	87.76 27	93.52 46	72.37 43	91.26 54	93.04 42	76.62 82	84.22 95	93.36 79	71.44 62	96.76 25	80.82 108	95.33 33	94.16 60
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MGCFI-Net		85.06 81	85.51 70	83.70 170	89.42 135	63.01 278	89.43 98	92.62 74	76.43 84	87.53 49	91.34 135	72.82 46	93.42 175	81.28 103	88.74 148	94.66 33

TSAR-MVS + GP.		85.71 65	85.33 74	86.84 52	91.34 84	72.50 36	89.07 118	87.28 272	76.41 85	85.80 66	90.22 173	74.15 32	95.37 81	81.82 98	91.88 89	92.65 147

HQP-NCC					89.33 140		89.17 110		76.41 85	77.23 227

ACMP_Plane					89.33 140		89.17 110		76.41 85	77.23 227

HQP-MVS		82.61 128	82.02 133	84.37 126	89.33 140	66.98 179	89.17 110	92.19 93	76.41 85	77.23 227	90.23 172	60.17 225	95.11 90	77.47 146	85.99 198	91.03 208

CANet_DTU		80.61 176	79.87 174	82.83 209	85.60 285	63.17 277	87.36 187	88.65 241	76.37 89	75.88 260	88.44 227	53.51 283	93.07 197	73.30 198	89.74 129	92.25 165

VNet		82.21 133	82.41 122	81.62 242	90.82 96	60.93 311	84.47 279	89.78 182	76.36 90	84.07 99	91.88 113	64.71 151	90.26 301	70.68 228	88.89 143	93.66 90

Vis-MVSNet		83.46 108	82.80 115	85.43 86	90.25 108	68.74 117	90.30 75	90.13 173	76.33 91	80.87 156	92.89 90	61.00 211	94.20 132	72.45 213	90.97 106	93.35 110
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ACMMP_NAP		88.05 17	88.08 18	87.94 19	93.70 41	73.05 22	90.86 60	93.59 24	76.27 92	88.14 37	95.09 19	71.06 68	96.67 29	87.67 40	96.37 14	94.09 65

fmvsm_s_conf0.5_n_10		86.38 49	86.76 43	85.24 91	87.33 233	67.30 170	89.50 95	90.98 142	76.25 93	90.56 18	94.75 25	68.38 105	94.24 131	90.80 7	92.32 84	94.19 59

alignmvs		85.48 69	85.32 75	85.96 73	89.51 130	69.47 98	89.74 86	92.47 77	76.17 94	87.73 48	91.46 132	70.32 76	93.78 154	81.51 99	88.95 142	94.63 34

MVS_111021_HR		85.14 78	84.75 83	86.32 61	91.65 81	72.70 30	85.98 236	90.33 165	76.11 95	82.08 132	91.61 126	71.36 64	94.17 135	81.02 105	92.58 78	92.08 176

HPM-MVS		87.11 35	86.98 38	87.50 39	93.88 39	72.16 47	92.19 34	93.33 32	76.07 96	83.81 105	93.95 63	69.77 84	96.01 54	85.15 57	94.66 47	94.32 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
h-mvs33		83.15 117	82.19 128	86.02 72	90.56 101	70.85 75	88.15 160	89.16 216	76.02 97	84.67 82	91.39 134	61.54 197	95.50 69	82.71 91	75.48 352	91.72 187

hse-mvs2		81.72 143	80.94 148	84.07 149	88.72 171	67.68 156	85.87 240	87.26 274	76.02 97	84.67 82	88.22 234	61.54 197	93.48 170	82.71 91	73.44 380	91.06 206

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 46	94.10 9	75.90 99	92.29 7	95.66 10	81.67 6	97.38 11	87.44 44	96.34 15	93.95 73
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CLD-MVS		82.31 132	81.65 138	84.29 133	88.47 179	67.73 154	85.81 244	92.35 83	75.78 100	78.33 201	86.58 284	64.01 157	94.35 124	76.05 167	87.48 169	90.79 217
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
viewmacassd2359aftdt		83.76 97	83.66 99	84.07 149	86.59 262	64.56 234	86.88 205	91.82 112	75.72 101	83.34 112	92.15 108	68.24 109	92.88 206	79.05 124	89.15 140	94.77 25

SF-MVS		88.46 12	88.74 12	87.64 35	92.78 66	71.95 51	92.40 25	94.74 2	75.71 102	89.16 25	95.10 18	75.65 21	96.19 47	87.07 45	96.01 17	94.79 23

testdata1							84.14 292		75.71 102

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 54	93.83 4	93.96 14	75.70 104	91.06 16	96.03 1	76.84 14	97.03 17	89.09 21	95.65 27	94.47 45
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
VPA-MVSNet		80.60 178	80.55 155	80.76 268	88.07 198	60.80 314	86.86 206	91.58 125	75.67 105	80.24 166	89.45 198	63.34 161	90.25 302	70.51 230	79.22 301	91.23 201

fmvsm_l_conf0.5_n_9		85.84 62	86.63 45	83.46 177	87.12 246	66.01 194	88.56 142	89.43 197	75.59 106	89.32 24	94.32 40	72.89 43	91.21 281	90.11 11	92.33 83	93.16 121

PGM-MVS		86.68 42	86.27 51	87.90 22	94.22 33	73.38 18	90.22 76	93.04 42	75.53 107	83.86 103	94.42 36	67.87 114	96.64 31	82.70 93	94.57 52	93.66 90

Effi-MVS+		83.62 104	83.08 108	85.24 91	88.38 184	67.45 163	88.89 123	89.15 217	75.50 108	82.27 128	88.28 231	69.61 86	94.45 123	77.81 141	87.84 162	93.84 80

viewcassd2359sk11		83.89 92	83.74 96	84.34 129	87.76 216	64.91 229	86.30 228	92.22 89	75.47 109	83.04 117	91.52 128	70.15 79	93.53 167	79.26 123	87.96 160	94.57 39

fmvsm_s_conf0.5_n_4		85.39 73	85.75 66	84.30 132	86.70 258	65.83 200	88.77 130	89.78 182	75.46 110	88.35 32	93.73 69	69.19 92	93.06 198	91.30 3	88.44 154	94.02 69

fmvsm_s_conf0.5_n_6		85.55 68	86.20 52	83.60 172	87.32 235	65.13 219	88.86 124	91.63 121	75.41 111	88.23 36	93.45 76	68.56 103	92.47 223	89.52 18	92.78 75	93.20 119

test_prior2							88.85 126		75.41 111	84.91 77	93.54 71	74.28 30		83.31 80	95.86 20

LPG-MVS_test		82.08 135	81.27 141	84.50 121	89.23 148	68.76 115	90.22 76	91.94 105	75.37 113	76.64 242	91.51 129	54.29 274	94.91 98	78.44 133	83.78 234	89.83 266

LGP-MVS_train				84.50 121	89.23 148	68.76 115		91.94 105	75.37 113	76.64 242	91.51 129	54.29 274	94.91 98	78.44 133	83.78 234	89.83 266

fmvsm_l_conf0.5_n_3		86.02 53	86.32 49	85.14 94	87.20 238	68.54 126	89.57 93	90.44 159	75.31 115	87.49 50	94.39 38	72.86 44	92.72 212	89.04 26	90.56 113	94.16 60

viewdifsd2359ckpt07		82.83 125	82.78 117	82.99 201	86.51 264	62.58 286	85.09 263	90.83 149	75.22 116	82.28 127	91.63 123	69.43 88	92.03 240	77.71 143	86.32 189	94.34 52

MG-MVS		83.41 109	83.45 102	83.28 184	92.74 67	62.28 295	88.17 158	89.50 195	75.22 116	81.49 143	92.74 98	66.75 124	95.11 90	72.85 203	91.58 96	92.45 157

SSC-MVS3.2		73.35 326	73.39 310	73.23 382	85.30 294	49.01 433	74.58 416	81.57 363	75.21 118	73.68 309	85.58 308	52.53 288	82.05 399	54.33 376	77.69 319	88.63 309

LCM-MVSNet-Re		77.05 269	76.94 252	77.36 339	87.20 238	51.60 419	80.06 358	80.46 378	75.20 119	67.69 376	86.72 274	62.48 179	88.98 327	63.44 294	89.25 136	91.51 192

SDMVSNet		80.38 185	80.18 164	80.99 262	89.03 157	64.94 226	80.45 352	89.40 198	75.19 120	76.61 244	89.98 175	60.61 219	87.69 347	76.83 157	83.55 243	90.33 239

sd_testset		77.70 257	77.40 242	78.60 312	89.03 157	60.02 325	79.00 373	85.83 303	75.19 120	76.61 244	89.98 175	54.81 266	85.46 372	62.63 303	83.55 243	90.33 239

MP-MVS-pluss		87.67 22	87.72 22	87.54 36	93.64 44	72.04 50	89.80 84	93.50 26	75.17 122	86.34 63	95.29 17	70.86 70	96.00 55	88.78 30	96.04 16	94.58 37
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test1111		79.43 207	79.18 196	80.15 282	89.99 117	53.31 407	87.33 189	77.05 412	75.04 123	80.23 167	92.77 97	48.97 343	92.33 232	68.87 250	92.40 82	94.81 22

Effi-MVS+-dtu		80.03 195	78.57 207	84.42 125	85.13 300	68.74 117	88.77 130	88.10 249	74.99 124	74.97 291	83.49 358	57.27 249	93.36 176	73.53 194	80.88 278	91.18 202

reproduce-ours		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 125	88.96 26	95.54 12	71.20 66	96.54 36	86.28 50	93.49 67	93.06 127

our_new_method		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 125	88.96 26	95.54 12	71.20 66	96.54 36	86.28 50	93.49 67	93.06 127

fmvsm_s_conf0.5_n_7		83.34 112	84.03 92	81.28 253	85.73 281	65.13 219	85.40 255	89.90 180	74.96 127	82.13 131	93.89 64	66.65 125	87.92 343	86.56 49	91.05 104	90.80 216

OMC-MVS		82.69 126	81.97 135	84.85 110	88.75 170	67.42 164	87.98 164	90.87 147	74.92 128	79.72 172	91.65 121	62.19 186	93.96 140	75.26 179	86.42 188	93.16 121

viewmanbaseed2359cas		83.66 100	83.55 100	84.00 160	86.81 254	64.53 235	86.65 215	91.75 117	74.89 129	83.15 116	91.68 119	68.74 101	92.83 210	79.02 125	89.24 137	94.63 34

test2506		77.30 266	76.49 263	79.74 290	90.08 112	52.02 412	87.86 172	63.10 455	74.88 130	80.16 168	92.79 95	38.29 419	92.35 230	68.74 252	92.50 80	94.86 19

ECVR-MVS		79.61 200	79.26 193	80.67 270	90.08 112	54.69 394	87.89 170	77.44 408	74.88 130	80.27 165	92.79 95	48.96 344	92.45 224	68.55 253	92.50 80	94.86 19

MonoMVSNet		76.49 282	75.80 271	78.58 313	81.55 380	58.45 338	86.36 226	86.22 296	74.87 132	74.73 295	83.73 351	51.79 307	88.73 332	70.78 225	72.15 389	88.55 312

nrg030		83.88 93	83.53 101	84.96 103	86.77 256	69.28 105	90.46 70	92.67 68	74.79 133	82.95 118	91.33 136	72.70 47	93.09 196	80.79 110	79.28 300	92.50 153

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 25	93.63 22	74.77 134	92.29 7	95.97 2	74.28 30	97.24 13	88.58 32	96.91 1	94.87 18
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
reproduce_model		87.28 32	87.39 30	86.95 50	93.10 58	71.24 65	91.60 45	93.19 36	74.69 135	88.80 29	95.61 11	70.29 77	96.44 39	86.20 52	93.08 71	93.16 121

MVS_111021_LR		82.61 128	82.11 129	84.11 142	88.82 162	71.58 57	85.15 260	86.16 298	74.69 135	80.47 164	91.04 146	62.29 183	90.55 299	80.33 115	90.08 122	90.20 244

EIA-MVS		83.31 115	82.80 115	84.82 111	89.59 126	65.59 208	88.21 156	92.68 67	74.66 137	78.96 184	86.42 289	69.06 95	95.26 83	75.54 175	90.09 121	93.62 97

TSAR-MVS + MP.		88.02 18	88.11 17	87.72 30	93.68 43	72.13 48	91.41 53	92.35 83	74.62 138	88.90 28	93.85 66	75.75 20	96.00 55	87.80 39	94.63 50	95.04 10
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SR-MVS		86.73 40	86.67 44	86.91 51	94.11 37	72.11 49	92.37 29	92.56 76	74.50 139	86.84 60	94.65 27	67.31 119	95.77 60	84.80 63	92.85 74	92.84 141

FOURS1					95.00 10	72.39 41	95.06 1	93.84 16	74.49 140	91.30 15

ACMP	74.13 6	81.51 154	80.57 154	84.36 127	89.42 135	68.69 122	89.97 80	91.50 130	74.46 141	75.04 289	90.41 165	53.82 280	94.54 117	77.56 145	82.91 254	89.86 265
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
EPP-MVSNet		83.40 110	83.02 110	84.57 119	90.13 110	64.47 240	92.32 31	90.73 151	74.45 142	79.35 180	91.10 143	69.05 96	95.12 88	72.78 204	87.22 173	94.13 62

fmvsm_s_conf0.5_n_2		84.04 90	84.11 91	83.81 168	86.17 271	65.00 224	86.96 200	87.28 272	74.35 143	88.25 35	94.23 46	61.82 192	92.60 215	89.85 12	88.09 159	93.84 80

fmvsm_s_conf0.1_n_2		83.80 95	83.79 95	83.83 166	85.62 284	64.94 226	87.03 197	86.62 290	74.32 144	87.97 43	94.33 39	60.67 216	92.60 215	89.72 14	87.79 163	93.96 71

save fliter					93.80 40	72.35 44	90.47 69	91.17 137	74.31 145

MVS_Test		83.15 117	83.06 109	83.41 181	86.86 251	63.21 274	86.11 234	92.00 101	74.31 145	82.87 120	89.44 199	70.03 80	93.21 185	77.39 148	88.50 153	93.81 82

myMVS_eth3d28		73.62 319	73.53 309	73.90 378	88.20 189	47.41 438	78.06 388	79.37 392	74.29 147	73.98 305	84.29 337	44.67 377	83.54 388	51.47 390	87.39 170	90.74 221

UniMVSNet_ETH3D		79.10 218	78.24 216	81.70 241	86.85 252	60.24 323	87.28 191	88.79 232	74.25 148	76.84 235	90.53 164	49.48 334	91.56 262	67.98 257	82.15 263	93.29 112

IterMVS-LS		80.06 194	79.38 188	82.11 233	85.89 277	63.20 275	86.79 209	89.34 200	74.19 149	75.45 270	86.72 274	66.62 126	92.39 227	72.58 206	76.86 328	90.75 220
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		80.52 182	79.98 170	82.12 231	84.28 317	63.19 276	86.41 223	88.95 228	74.18 150	78.69 189	87.54 254	66.62 126	92.43 225	72.57 207	80.57 284	90.74 221

Vis-MVSNet (Re-imp)		78.36 237	78.45 209	78.07 326	88.64 174	51.78 418	86.70 213	79.63 390	74.14 151	75.11 286	90.83 154	61.29 205	89.75 311	58.10 348	91.60 94	92.69 145

v8		79.97 197	79.02 199	82.80 212	84.09 322	64.50 239	87.96 165	90.29 168	74.13 152	75.24 282	86.81 271	62.88 175	93.89 151	74.39 187	75.40 357	90.00 257

guyue		81.13 159	80.64 153	82.60 223	86.52 263	63.92 252	86.69 214	87.73 263	73.97 153	80.83 158	89.69 185	56.70 255	91.33 277	78.26 140	85.40 211	92.54 150

CSCG		86.41 48	86.19 54	87.07 46	92.91 63	72.48 37	90.81 61	93.56 25	73.95 154	83.16 115	91.07 145	75.94 18	95.19 85	79.94 119	94.38 58	93.55 102

thres100view900		76.50 279	75.55 278	79.33 299	89.52 129	56.99 362	85.83 243	83.23 339	73.94 155	76.32 251	87.12 266	51.89 304	91.95 245	48.33 410	83.75 237	89.07 284

9.14			88.26 16		92.84 65		91.52 51	94.75 1	73.93 156	88.57 31	94.67 26	75.57 22	95.79 59	86.77 47	95.76 23

HPM-MVS_fast		85.35 75	84.95 81	86.57 59	93.69 42	70.58 80	92.15 36	91.62 122	73.89 157	82.67 125	94.09 52	62.60 176	95.54 66	80.93 106	92.93 73	93.57 100

PAPM_NR		83.02 121	82.41 122	84.82 111	92.47 72	66.37 188	87.93 168	91.80 113	73.82 158	77.32 224	90.66 158	67.90 113	94.90 100	70.37 231	89.48 134	93.19 120

thres600view7		76.50 279	75.44 279	79.68 292	89.40 137	57.16 359	85.53 252	83.23 339	73.79 159	76.26 252	87.09 267	51.89 304	91.89 248	48.05 415	83.72 240	90.00 257

testing91		76.54 277	75.66 276	79.18 303	88.43 182	55.89 380	81.08 339	83.00 346	73.76 160	75.34 275	84.29 337	46.20 365	90.07 305	64.33 288	84.50 221	91.58 190

AstraMVS		80.81 166	80.14 167	82.80 212	86.05 276	63.96 249	86.46 222	85.90 302	73.71 161	80.85 157	90.56 162	54.06 278	91.57 261	79.72 121	83.97 232	92.86 139

v7n		78.97 222	77.58 238	83.14 192	83.45 339	65.51 209	88.32 153	91.21 135	73.69 162	72.41 326	86.32 292	57.93 240	93.81 153	69.18 246	75.65 348	90.11 249

dcpmvs_2		85.63 66	86.15 56	84.06 152	91.71 80	64.94 226	86.47 221	91.87 109	73.63 163	86.60 62	93.02 88	76.57 15	91.87 250	83.36 79	92.15 85	95.35 3

v2v482		80.23 191	79.29 192	83.05 198	83.62 335	64.14 246	87.04 196	89.97 177	73.61 164	78.18 205	87.22 262	61.10 209	93.82 152	76.11 165	76.78 331	91.18 202

Baseline_NR-MVSNet		78.15 243	78.33 214	77.61 335	85.79 279	56.21 377	86.78 210	85.76 304	73.60 165	77.93 211	87.57 251	65.02 148	88.99 326	67.14 267	75.33 359	87.63 329

BH-RMVSNet		79.61 200	78.44 210	83.14 192	89.38 139	65.93 197	84.95 267	87.15 277	73.56 166	78.19 204	89.79 183	56.67 256	93.36 176	59.53 332	86.74 183	90.13 247

APD-MVS_3200maxsize		85.97 57	85.88 61	86.22 63	92.69 68	69.53 95	91.93 38	92.99 50	73.54 167	85.94 64	94.51 31	65.80 142	95.61 63	83.04 84	92.51 79	93.53 104

SR-MVS-dyc-post		85.77 63	85.61 68	86.23 62	93.06 60	70.63 78	91.88 39	92.27 85	73.53 168	85.69 68	94.45 33	65.00 150	95.56 64	82.75 89	91.87 90	92.50 153

RE-MVS-def			85.48 71		93.06 60	70.63 78	91.88 39	92.27 85	73.53 168	85.69 68	94.45 33	63.87 158		82.75 89	91.87 90	92.50 153

reproduce_monomvs		75.40 300	74.38 298	78.46 319	83.92 327	57.80 351	83.78 297	86.94 281	73.47 170	72.25 329	84.47 331	38.74 415	89.27 320	75.32 178	70.53 399	88.31 316

test_fmvsmconf_n		85.92 58	86.04 59	85.57 83	85.03 303	69.51 96	89.62 92	90.58 154	73.42 171	87.75 46	94.02 56	72.85 45	93.24 182	90.37 8	90.75 110	93.96 71

tfpn200view9		76.42 283	75.37 283	79.55 297	89.13 152	57.65 353	85.17 258	83.60 331	73.41 172	76.45 247	86.39 290	52.12 296	91.95 245	48.33 410	83.75 237	89.07 284

thres400		76.50 279	75.37 283	79.86 287	89.13 152	57.65 353	85.17 258	83.60 331	73.41 172	76.45 247	86.39 290	52.12 296	91.95 245	48.33 410	83.75 237	90.00 257

diffmvs_AUTHOR		82.38 131	82.27 127	82.73 220	83.26 343	63.80 254	83.89 295	89.76 184	73.35 174	82.37 126	90.84 153	66.25 133	90.79 293	82.77 88	87.93 161	93.59 99

test_fmvsmconf0.1_n		85.61 67	85.65 67	85.50 84	82.99 355	69.39 103	89.65 89	90.29 168	73.31 175	87.77 45	94.15 50	71.72 57	93.23 183	90.31 9	90.67 112	93.89 77

testing99		76.09 289	75.12 288	79.00 304	88.16 191	55.50 386	80.79 343	81.40 366	73.30 176	75.17 283	84.27 340	44.48 380	90.02 306	64.28 289	84.22 230	91.48 195

v148		78.72 228	77.80 229	81.47 246	82.73 361	61.96 299	86.30 228	88.08 250	73.26 177	76.18 255	85.47 311	62.46 180	92.36 229	71.92 217	73.82 376	90.09 251

FA-MVS(test-final)		80.96 162	79.91 172	84.10 143	88.30 187	65.01 223	84.55 278	90.01 176	73.25 178	79.61 173	87.57 251	58.35 238	94.72 111	71.29 222	86.25 192	92.56 149

test_fmvsmconf0.01_n		84.73 85	84.52 87	85.34 88	80.25 397	69.03 106	89.47 96	89.65 189	73.24 179	86.98 58	94.27 43	66.62 126	93.23 183	90.26 10	89.95 125	93.78 86

viewdifsd2359ckpt11		80.37 187	79.73 178	82.30 229	83.70 333	62.39 290	84.20 289	86.67 286	73.22 180	80.90 154	90.62 159	63.00 173	91.56 262	76.81 158	78.44 307	92.95 136

viewmsd2359difaftdt		80.37 187	79.73 178	82.30 229	83.70 333	62.39 290	84.20 289	86.67 286	73.22 180	80.90 154	90.62 159	63.00 173	91.56 262	76.81 158	78.44 307	92.95 136

v10		79.74 199	78.67 204	82.97 204	84.06 323	64.95 225	87.88 171	90.62 153	73.11 182	75.11 286	86.56 285	61.46 200	94.05 139	73.68 192	75.55 350	89.90 263

MCST-MVS		87.37 31	87.25 32	87.73 28	94.53 17	72.46 40	89.82 82	93.82 17	73.07 183	84.86 80	92.89 90	76.22 17	96.33 41	84.89 61	95.13 36	94.40 48

baseline1		76.98 271	76.75 259	77.66 333	88.13 194	55.66 384	85.12 261	81.89 359	73.04 184	76.79 237	88.90 212	62.43 181	87.78 346	63.30 296	71.18 396	89.55 275

APD-MVS		87.44 26	87.52 27	87.19 43	94.24 32	72.39 41	91.86 41	92.83 61	73.01 185	88.58 30	94.52 28	73.36 35	96.49 38	84.26 70	95.01 37	92.70 143
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
diffmvs		82.10 134	81.88 136	82.76 218	83.00 353	63.78 256	83.68 300	89.76 184	72.94 186	82.02 133	89.85 178	65.96 141	90.79 293	82.38 95	87.30 172	93.71 88
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
K. test v3		71.19 346	68.51 358	79.21 302	83.04 352	57.78 352	84.35 286	76.91 413	72.90 187	62.99 419	82.86 370	39.27 411	91.09 287	61.65 314	52.66 446	88.75 304

MVSMamba_PlusPlus		85.99 55	85.96 60	86.05 69	91.09 88	67.64 157	89.63 91	92.65 71	72.89 188	84.64 85	91.71 118	71.85 54	96.03 51	84.77 64	94.45 56	94.49 44

GDP-MVS		83.52 106	82.64 118	86.16 65	88.14 193	68.45 128	89.13 115	92.69 66	72.82 189	83.71 106	91.86 115	55.69 261	95.35 82	80.03 117	89.74 129	94.69 29

fmvsm_s_conf0.5_n_5		85.22 77	85.55 69	84.25 139	86.26 267	67.40 166	89.18 109	89.31 206	72.50 190	88.31 33	93.86 65	69.66 85	91.96 244	89.81 13	91.05 104	93.38 107

Fast-Effi-MVS+-dtu		78.02 247	76.49 263	82.62 222	83.16 349	66.96 181	86.94 202	87.45 270	72.45 191	71.49 338	84.17 342	54.79 270	91.58 259	67.61 260	80.31 287	89.30 282

PHI-MVS		86.43 46	86.17 55	87.24 42	90.88 95	70.96 70	92.27 33	94.07 10	72.45 191	85.22 73	91.90 112	69.47 87	96.42 40	83.28 81	95.94 19	94.35 51

thres200		75.55 295	74.47 296	78.82 308	87.78 214	57.85 349	83.07 318	83.51 334	72.44 193	75.84 261	84.42 332	52.08 299	91.75 253	47.41 417	83.64 242	86.86 352

test_yl		81.17 157	80.47 158	83.24 187	89.13 152	63.62 257	86.21 231	89.95 178	72.43 194	81.78 138	89.61 189	57.50 246	93.58 162	70.75 226	86.90 179	92.52 151

DCV-MVSNet		81.17 157	80.47 158	83.24 187	89.13 152	63.62 257	86.21 231	89.95 178	72.43 194	81.78 138	89.61 189	57.50 246	93.58 162	70.75 226	86.90 179	92.52 151

viewdifsd2359ckpt13		82.91 123	82.29 126	84.77 114	86.96 250	66.90 183	87.47 181	91.62 122	72.19 196	81.68 140	90.71 156	66.92 123	93.28 178	75.90 169	87.15 175	94.12 63

BH-untuned		79.47 205	78.60 206	82.05 234	89.19 150	65.91 198	86.07 235	88.52 244	72.18 197	75.42 271	87.69 248	61.15 208	93.54 166	60.38 324	86.83 182	86.70 356

TransMVSNet (Re)		75.39 301	74.56 294	77.86 329	85.50 289	57.10 361	86.78 210	86.09 300	72.17 198	71.53 337	87.34 257	63.01 172	89.31 319	56.84 361	61.83 428	87.17 342

GA-MVS		76.87 273	75.17 287	81.97 237	82.75 360	62.58 286	81.44 336	86.35 295	72.16 199	74.74 294	82.89 369	46.20 365	92.02 242	68.85 251	81.09 275	91.30 200

VortexMVS		78.57 233	77.89 225	80.59 271	85.89 277	62.76 285	85.61 245	89.62 191	72.06 200	74.99 290	85.38 313	55.94 260	90.77 296	74.99 180	76.58 332	88.23 317

mmtdpeth		74.16 312	73.01 316	77.60 337	83.72 332	61.13 307	85.10 262	85.10 311	72.06 200	77.21 231	80.33 398	43.84 385	85.75 366	77.14 151	52.61 447	85.91 371

v1144		80.03 195	79.03 198	83.01 200	83.78 330	64.51 237	87.11 195	90.57 156	71.96 202	78.08 208	86.20 294	61.41 201	93.94 143	74.93 181	77.23 322	90.60 227

viewdifsd2359ckpt09		83.34 112	82.55 120	85.70 77	87.64 222	67.72 155	88.43 145	91.68 119	71.91 203	81.65 141	90.68 157	67.10 122	94.75 109	76.17 164	87.70 165	94.62 36

PS-MVSNAJss		82.07 136	81.31 140	84.34 129	86.51 264	67.27 172	89.27 106	91.51 127	71.75 204	79.37 179	90.22 173	63.15 168	94.27 127	77.69 144	82.36 262	91.49 194

EPNet_dtu		75.46 297	74.86 289	77.23 342	82.57 365	54.60 395	86.89 204	83.09 343	71.64 205	66.25 398	85.86 300	55.99 259	88.04 342	54.92 372	86.55 186	89.05 289
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GBi-Net		78.40 235	77.40 242	81.40 249	87.60 223	63.01 278	88.39 148	89.28 207	71.63 206	75.34 275	87.28 258	54.80 267	91.11 282	62.72 299	79.57 294	90.09 251

test1		78.40 235	77.40 242	81.40 249	87.60 223	63.01 278	88.39 148	89.28 207	71.63 206	75.34 275	87.28 258	54.80 267	91.11 282	62.72 299	79.57 294	90.09 251

FMVSNet2		78.20 241	77.21 246	81.20 256	87.60 223	62.89 284	87.47 181	89.02 223	71.63 206	75.29 281	87.28 258	54.80 267	91.10 285	62.38 304	79.38 298	89.61 273

patch_mono-2		83.65 101	84.54 85	80.99 262	90.06 116	65.83 200	84.21 288	88.74 237	71.60 209	85.01 74	92.44 100	74.51 26	83.50 389	82.15 96	92.15 85	93.64 96

V42		79.38 211	78.24 216	82.83 209	81.10 389	65.50 210	85.55 250	89.82 181	71.57 210	78.21 203	86.12 296	60.66 217	93.18 191	75.64 172	75.46 354	89.81 268

API-MVS		81.99 138	81.23 142	84.26 138	90.94 93	70.18 87	91.10 58	89.32 205	71.51 211	78.66 191	88.28 231	65.26 145	95.10 93	64.74 286	91.23 102	87.51 333

tttt0517		79.40 209	77.91 223	83.90 165	88.10 196	63.84 253	88.37 151	84.05 326	71.45 212	76.78 238	89.12 203	49.93 331	94.89 101	70.18 235	83.18 252	92.96 135

pm-mvs1		77.25 267	76.68 261	78.93 306	84.22 319	58.62 337	86.41 223	88.36 246	71.37 213	73.31 313	88.01 241	61.22 207	89.15 324	64.24 290	73.01 383	89.03 290

Elysia		81.53 150	80.16 165	85.62 80	85.51 287	68.25 135	88.84 127	92.19 93	71.31 214	80.50 162	89.83 179	46.89 355	94.82 104	76.85 154	89.57 131	93.80 84

StellarMVS		81.53 150	80.16 165	85.62 80	85.51 287	68.25 135	88.84 127	92.19 93	71.31 214	80.50 162	89.83 179	46.89 355	94.82 104	76.85 154	89.57 131	93.80 84

testing222		74.04 314	72.66 320	78.19 322	87.89 206	55.36 387	81.06 340	79.20 395	71.30 216	74.65 297	83.57 357	39.11 414	88.67 334	51.43 392	85.75 205	90.53 230

GeoE		81.71 144	81.01 147	83.80 169	89.51 130	64.45 241	88.97 120	88.73 238	71.27 217	78.63 192	89.76 184	66.32 132	93.20 188	69.89 239	86.02 197	93.74 87

tt0805		78.73 227	77.83 227	81.43 247	85.17 296	60.30 322	89.41 101	90.90 145	71.21 218	77.17 232	88.73 216	46.38 360	93.21 185	72.57 207	78.96 302	90.79 217

FMVSNet3		77.88 251	76.85 254	80.97 264	86.84 253	62.36 292	86.52 220	88.77 233	71.13 219	75.34 275	86.66 280	54.07 277	91.10 285	62.72 299	79.57 294	89.45 277

VDDNet		81.52 152	80.67 152	84.05 155	90.44 104	64.13 247	89.73 87	85.91 301	71.11 220	83.18 114	93.48 73	50.54 321	93.49 169	73.40 197	88.25 156	94.54 43

fmvsm_s_conf0.5_n		83.80 95	83.71 97	84.07 149	86.69 259	67.31 169	89.46 97	83.07 344	71.09 221	86.96 59	93.70 70	69.02 98	91.47 271	88.79 29	84.62 220	93.44 106

XVG-OURS		80.41 183	79.23 194	83.97 162	85.64 283	69.02 108	83.03 320	90.39 160	71.09 221	77.63 218	91.49 131	54.62 273	91.35 275	75.71 171	83.47 246	91.54 191

SSM_0407		81.58 149	80.48 157	84.87 109	88.81 163	67.96 145	87.37 186	89.25 211	71.06 223	79.48 176	90.39 166	59.57 227	94.48 122	72.45 213	85.93 200	92.18 170

SSM_0404		81.91 139	80.84 150	85.13 97	89.24 147	68.26 133	87.84 173	89.25 211	71.06 223	80.62 160	90.39 166	59.57 227	94.65 115	72.45 213	87.19 174	92.47 156

SixPastTwentyTwo		73.37 323	71.26 337	79.70 291	85.08 301	57.89 348	85.57 246	83.56 333	71.03 225	65.66 401	85.88 299	42.10 397	92.57 217	59.11 336	63.34 423	88.65 308

ZD-MVS					94.38 25	72.22 46		92.67 68	70.98 226	87.75 46	94.07 53	74.01 33	96.70 27	84.66 65	94.84 44

mamba_0408		79.37 212	77.52 239	84.93 106	88.81 163	67.96 145	65.03 452	88.66 239	70.96 227	79.48 176	89.80 181	58.69 233	94.65 115	70.35 232	85.93 200	92.18 170

SSM_04072		77.67 259	77.52 239	78.12 324	88.81 163	67.96 145	65.03 452	88.66 239	70.96 227	79.48 176	89.80 181	58.69 233	74.23 445	70.35 232	85.93 200	92.18 170

v1192		79.59 202	78.43 211	83.07 197	83.55 337	64.52 236	86.93 203	90.58 154	70.83 229	77.78 215	85.90 298	59.15 231	93.94 143	73.96 191	77.19 324	90.76 219

Fast-Effi-MVS+		80.81 166	79.92 171	83.47 176	88.85 159	64.51 237	85.53 252	89.39 199	70.79 230	78.49 196	85.06 322	67.54 116	93.58 162	67.03 269	86.58 185	92.32 162

PS-MVSNAJ		81.69 145	81.02 146	83.70 170	89.51 130	68.21 138	84.28 287	90.09 174	70.79 230	81.26 149	85.62 307	63.15 168	94.29 125	75.62 173	88.87 144	88.59 310

LTVRE_ROB	69.57 13	76.25 286	74.54 295	81.41 248	88.60 175	64.38 243	79.24 368	89.12 220	70.76 232	69.79 359	87.86 244	49.09 341	93.20 188	56.21 367	80.16 288	86.65 357
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
testing11		75.14 303	74.01 301	78.53 316	88.16 191	56.38 373	80.74 346	80.42 380	70.67 233	72.69 323	83.72 352	43.61 387	89.86 308	62.29 306	83.76 236	89.36 280

fmvsm_s_conf0.1_n		83.56 105	83.38 104	84.10 143	84.86 305	67.28 171	89.40 102	83.01 345	70.67 233	87.08 56	93.96 62	68.38 105	91.45 272	88.56 33	84.50 221	93.56 101

xiu_mvs_v2_base		81.69 145	81.05 145	83.60 172	89.15 151	68.03 143	84.46 281	90.02 175	70.67 233	81.30 148	86.53 287	63.17 167	94.19 134	75.60 174	88.54 151	88.57 311

XVG-OURS-SEG-HR		80.81 166	79.76 177	83.96 163	85.60 285	68.78 114	83.54 307	90.50 157	70.66 236	76.71 240	91.66 120	60.69 215	91.26 278	76.94 153	81.58 270	91.83 180

Anonymous202405211		78.25 238	77.01 249	81.99 236	91.03 90	60.67 316	84.77 270	83.90 328	70.65 237	80.00 169	91.20 140	41.08 404	91.43 273	65.21 281	85.26 212	93.85 78

DP-MVS Recon		83.11 120	82.09 131	86.15 66	94.44 19	70.92 73	88.79 129	92.20 92	70.53 238	79.17 182	91.03 148	64.12 156	96.03 51	68.39 256	90.14 120	91.50 193

icg_test_0407_2		78.92 224	78.93 201	78.90 307	87.13 241	63.59 261	76.58 399	89.33 201	70.51 239	77.82 212	89.03 206	61.84 190	81.38 404	72.56 209	85.56 207	91.74 183

IMVS_0407		80.61 176	79.90 173	82.75 219	87.13 241	63.59 261	85.33 256	89.33 201	70.51 239	77.82 212	89.03 206	61.84 190	92.91 204	72.56 209	85.56 207	91.74 183

IMVS_0404		77.16 268	76.42 266	79.37 298	87.13 241	63.59 261	77.12 397	89.33 201	70.51 239	66.22 399	89.03 206	50.36 323	82.78 394	72.56 209	85.56 207	91.74 183

IMVS_0403		80.80 169	80.12 168	82.87 208	87.13 241	63.59 261	85.19 257	89.33 201	70.51 239	78.49 196	89.03 206	63.26 164	93.27 180	72.56 209	85.56 207	91.74 183

FMVSNet1		77.44 262	76.12 270	81.40 249	86.81 254	63.01 278	88.39 148	89.28 207	70.49 243	74.39 301	87.28 258	49.06 342	91.11 282	60.91 320	78.52 305	90.09 251

LuminaMVS		80.68 174	79.62 183	83.83 166	85.07 302	68.01 144	86.99 199	88.83 230	70.36 244	81.38 144	87.99 242	50.11 326	92.51 222	79.02 125	86.89 181	90.97 211

testing3		68.56 375	67.67 374	71.22 403	87.33 233	42.87 453	83.06 319	71.54 433	70.36 244	69.08 365	84.38 334	30.33 441	85.69 368	37.50 446	75.45 355	85.09 386

ab-mvs		79.51 203	78.97 200	81.14 258	88.46 180	60.91 312	83.84 296	89.24 213	70.36 244	79.03 183	88.87 214	63.23 166	90.21 303	65.12 282	82.57 260	92.28 164

tfpnnormal		74.39 308	73.16 314	78.08 325	86.10 275	58.05 343	84.65 275	87.53 267	70.32 247	71.22 341	85.63 306	54.97 265	89.86 308	43.03 434	75.02 364	86.32 360

ACMM	73.20 8	80.78 173	79.84 175	83.58 174	89.31 143	68.37 130	89.99 79	91.60 124	70.28 248	77.25 225	89.66 187	53.37 285	93.53 167	74.24 189	82.85 255	88.85 299
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.5_n_a		83.63 103	83.41 103	84.28 134	86.14 272	68.12 139	89.43 98	82.87 349	70.27 249	87.27 55	93.80 68	69.09 93	91.58 259	88.21 37	83.65 241	93.14 124

ACMH+	68.96 14	76.01 290	74.01 301	82.03 235	88.60 175	65.31 215	88.86 124	87.55 266	70.25 250	67.75 375	87.47 256	41.27 402	93.19 190	58.37 345	75.94 345	87.60 330

IB-MVS	68.01 15	75.85 292	73.36 312	83.31 183	84.76 308	66.03 192	83.38 309	85.06 312	70.21 251	69.40 361	81.05 388	45.76 370	94.66 114	65.10 283	75.49 351	89.25 283
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
thisisatest0530		79.40 209	77.76 232	84.31 131	87.69 220	65.10 222	87.36 187	84.26 324	70.04 252	77.42 221	88.26 233	49.94 329	94.79 108	70.20 234	84.70 219	93.03 130

mvsmamba		80.60 178	79.38 188	84.27 136	89.74 124	67.24 174	87.47 181	86.95 280	70.02 253	75.38 273	88.93 211	51.24 312	92.56 218	75.47 177	89.22 138	93.00 133

test_fmvsmvis_n_1920		84.02 91	83.87 93	84.49 123	84.12 321	69.37 104	88.15 160	87.96 255	70.01 254	83.95 102	93.23 81	68.80 100	91.51 269	88.61 31	89.96 124	92.57 148

v144192		79.47 205	78.37 212	82.78 216	83.35 340	63.96 249	86.96 200	90.36 164	69.99 255	77.50 219	85.67 305	60.66 217	93.77 156	74.27 188	76.58 332	90.62 225

test_fmvsm_n_1920		85.29 76	85.34 73	85.13 97	86.12 273	69.93 88	88.65 138	90.78 150	69.97 256	88.27 34	93.98 61	71.39 63	91.54 266	88.49 34	90.45 115	93.91 74

c3_l		78.75 226	77.91 223	81.26 254	82.89 358	61.56 304	84.09 293	89.13 219	69.97 256	75.56 265	84.29 337	66.36 131	92.09 239	73.47 196	75.48 352	90.12 248

v1921920		79.22 214	78.03 220	82.80 212	83.30 342	63.94 251	86.80 208	90.33 165	69.91 258	77.48 220	85.53 309	58.44 237	93.75 158	73.60 193	76.85 329	90.71 223

ACMH	67.68 16	75.89 291	73.93 303	81.77 240	88.71 172	66.61 185	88.62 139	89.01 224	69.81 259	66.78 389	86.70 278	41.95 399	91.51 269	55.64 368	78.14 313	87.17 342
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.1_n_a		83.32 114	82.99 111	84.28 134	83.79 329	68.07 141	89.34 105	82.85 350	69.80 260	87.36 54	94.06 54	68.34 107	91.56 262	87.95 38	83.46 247	93.21 117

DPM-MVS		84.93 82	84.29 89	86.84 52	90.20 109	73.04 23	87.12 194	93.04 42	69.80 260	82.85 121	91.22 139	73.06 41	96.02 53	76.72 161	94.63 50	91.46 197

MAR-MVS		81.84 141	80.70 151	85.27 90	91.32 85	71.53 58	89.82 82	90.92 144	69.77 262	78.50 195	86.21 293	62.36 182	94.52 119	65.36 280	92.05 88	89.77 269
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
XVG-ACMP-BASELINE		76.11 288	74.27 300	81.62 242	83.20 346	64.67 233	83.60 304	89.75 186	69.75 263	71.85 333	87.09 267	32.78 434	92.11 238	69.99 238	80.43 286	88.09 321

BH-w/o		78.21 240	77.33 245	80.84 266	88.81 163	65.13 219	84.87 268	87.85 260	69.75 263	74.52 299	84.74 329	61.34 203	93.11 195	58.24 347	85.84 203	84.27 394

v1240		78.99 221	77.78 230	82.64 221	83.21 345	63.54 265	86.62 217	90.30 167	69.74 265	77.33 223	85.68 304	57.04 252	93.76 157	73.13 201	76.92 326	90.62 225

ET-MVSNet_ETH3D		78.63 230	76.63 262	84.64 118	86.73 257	69.47 98	85.01 265	84.61 317	69.54 266	66.51 396	86.59 282	50.16 325	91.75 253	76.26 163	84.24 229	92.69 145

eth_miper_zixun_eth		77.92 250	76.69 260	81.61 244	83.00 353	61.98 298	83.15 314	89.20 215	69.52 267	74.86 293	84.35 336	61.76 193	92.56 218	71.50 220	72.89 384	90.28 242

PVSNet_Blended_VisFu		82.62 127	81.83 137	84.96 103	90.80 97	69.76 93	88.74 134	91.70 118	69.39 268	78.96 184	88.46 226	65.47 144	94.87 103	74.42 186	88.57 150	90.24 243

mvs_tets		79.13 217	77.77 231	83.22 189	84.70 309	66.37 188	89.17 110	90.19 171	69.38 269	75.40 272	89.46 196	44.17 383	93.15 192	76.78 160	80.70 282	90.14 246

PVSNet_BlendedMVS		80.60 178	80.02 169	82.36 228	88.85 159	65.40 211	86.16 233	92.00 101	69.34 270	78.11 206	86.09 297	66.02 139	94.27 127	71.52 218	82.06 265	87.39 335

SD_0403		74.65 307	74.77 291	74.29 373	86.20 270	47.42 437	83.71 299	85.12 310	69.30 271	68.50 371	87.95 243	59.40 229	86.05 363	49.38 404	83.35 248	89.40 278

AdaColmap		80.58 181	79.42 187	84.06 152	93.09 59	68.91 111	89.36 104	88.97 227	69.27 272	75.70 263	89.69 185	57.20 251	95.77 60	63.06 297	88.41 155	87.50 334

ETVMVS		72.25 339	71.05 338	75.84 351	87.77 215	51.91 415	79.39 366	74.98 421	69.26 273	73.71 308	82.95 367	40.82 406	86.14 362	46.17 423	84.43 226	89.47 276

ITE_SJBPF				78.22 321	81.77 376	60.57 317		83.30 337	69.25 274	67.54 377	87.20 263	36.33 427	87.28 352	54.34 375	74.62 368	86.80 353

cl____		77.72 255	76.76 257	80.58 272	82.49 367	60.48 319	83.09 316	87.87 258	69.22 275	74.38 302	85.22 318	62.10 187	91.53 267	71.09 223	75.41 356	89.73 271

DIV-MVS_self_test		77.72 255	76.76 257	80.58 272	82.48 368	60.48 319	83.09 316	87.86 259	69.22 275	74.38 302	85.24 316	62.10 187	91.53 267	71.09 223	75.40 357	89.74 270

jajsoiax		79.29 213	77.96 221	83.27 185	84.68 310	66.57 186	89.25 107	90.16 172	69.20 277	75.46 269	89.49 193	45.75 371	93.13 194	76.84 156	80.80 280	90.11 249

IterMVS-SCA-FT		75.43 298	73.87 305	80.11 283	82.69 362	64.85 230	81.57 333	83.47 335	69.16 278	70.49 345	84.15 343	51.95 302	88.15 340	69.23 245	72.14 390	87.34 337

CL-MVSNet_self_test		72.37 337	71.46 332	75.09 363	79.49 410	53.53 403	80.76 345	85.01 314	69.12 279	70.51 344	82.05 382	57.92 241	84.13 383	52.27 386	66.00 417	87.60 330

AUN-MVS		79.21 215	77.60 237	84.05 155	88.71 172	67.61 158	85.84 242	87.26 274	69.08 280	77.23 227	88.14 239	53.20 287	93.47 171	75.50 176	73.45 379	91.06 206

xiu_mvs_v1_base_debu		80.80 169	79.72 180	84.03 157	87.35 228	70.19 84	85.56 247	88.77 233	69.06 281	81.83 134	88.16 235	50.91 315	92.85 207	78.29 137	87.56 166	89.06 286

xiu_mvs_v1_base		80.80 169	79.72 180	84.03 157	87.35 228	70.19 84	85.56 247	88.77 233	69.06 281	81.83 134	88.16 235	50.91 315	92.85 207	78.29 137	87.56 166	89.06 286

xiu_mvs_v1_base_debi		80.80 169	79.72 180	84.03 157	87.35 228	70.19 84	85.56 247	88.77 233	69.06 281	81.83 134	88.16 235	50.91 315	92.85 207	78.29 137	87.56 166	89.06 286

MVSTER		79.01 220	77.88 226	82.38 227	83.07 350	64.80 231	84.08 294	88.95 228	69.01 284	78.69 189	87.17 265	54.70 271	92.43 225	74.69 182	80.57 284	89.89 264

cl22		78.07 245	77.01 249	81.23 255	82.37 370	61.83 301	83.55 305	87.98 254	68.96 285	75.06 288	83.87 345	61.40 202	91.88 249	73.53 194	76.39 337	89.98 260

miper_ehance_all_eth		78.59 232	77.76 232	81.08 260	82.66 363	61.56 304	83.65 301	89.15 217	68.87 286	75.55 266	83.79 349	66.49 129	92.03 240	73.25 199	76.39 337	89.64 272

PAPR		81.66 147	80.89 149	83.99 161	90.27 107	64.00 248	86.76 212	91.77 116	68.84 287	77.13 234	89.50 192	67.63 115	94.88 102	67.55 261	88.52 152	93.09 125

CPTT-MVS		83.73 98	83.33 106	84.92 107	93.28 49	70.86 74	92.09 37	90.38 161	68.75 288	79.57 174	92.83 92	60.60 220	93.04 201	80.92 107	91.56 97	90.86 215

train_agg		86.43 46	86.20 52	87.13 45	93.26 52	72.96 25	88.75 132	91.89 107	68.69 289	85.00 75	93.10 83	74.43 27	95.41 76	84.97 58	95.71 25	93.02 131

test_8					93.13 56	72.57 35	88.68 137	91.84 111	68.69 289	84.87 79	93.10 83	74.43 27	95.16 86

dmvs_re		71.14 347	70.58 342	72.80 389	81.96 373	59.68 328	75.60 407	79.34 393	68.55 291	69.27 364	80.72 394	49.42 335	76.54 426	52.56 385	77.79 316	82.19 419

MVSFormer		82.85 124	82.05 132	85.24 91	87.35 228	70.21 82	90.50 67	90.38 161	68.55 291	81.32 145	89.47 194	61.68 194	93.46 172	78.98 128	90.26 118	92.05 177

test_djsdf		80.30 190	79.32 191	83.27 185	83.98 325	65.37 214	90.50 67	90.38 161	68.55 291	76.19 254	88.70 217	56.44 258	93.46 172	78.98 128	80.14 290	90.97 211

TEST9					93.26 52	72.96 25	88.75 132	91.89 107	68.44 294	85.00 75	93.10 83	74.36 29	95.41 76

FE-MVS		77.78 253	75.68 274	84.08 148	88.09 197	66.00 195	83.13 315	87.79 261	68.42 295	78.01 209	85.23 317	45.50 374	95.12 88	59.11 336	85.83 204	91.11 204

CDPH-MVS		85.76 64	85.29 77	87.17 44	93.49 47	71.08 66	88.58 141	92.42 81	68.32 296	84.61 86	93.48 73	72.32 48	96.15 49	79.00 127	95.43 30	94.28 56

PC_three_1452									68.21 297	92.02 12	94.00 58	82.09 5	95.98 57	84.58 66	96.68 2	94.95 12

fmvsm_l_conf0.5_n		84.47 86	84.54 85	84.27 136	85.42 290	68.81 112	88.49 144	87.26 274	68.08 298	88.03 40	93.49 72	72.04 53	91.77 252	88.90 28	89.14 141	92.24 167

IterMVS		74.29 309	72.94 317	78.35 320	81.53 381	63.49 267	81.58 332	82.49 353	68.06 299	69.99 354	83.69 353	51.66 309	85.54 370	65.85 277	71.64 393	86.01 368
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_testset		62.63 404	64.11 395	58.19 434	78.55 416	24.76 472	75.28 408	65.94 449	67.91 300	60.34 428	76.01 431	53.56 282	73.94 447	31.79 452	67.65 410	75.88 441

TAMVS		78.89 225	77.51 241	83.03 199	87.80 211	67.79 153	84.72 271	85.05 313	67.63 301	76.75 239	87.70 247	62.25 184	90.82 292	58.53 343	87.13 176	90.49 232

PVSNet_Blended		80.98 161	80.34 160	82.90 206	88.85 159	65.40 211	84.43 283	92.00 101	67.62 302	78.11 206	85.05 323	66.02 139	94.27 127	71.52 218	89.50 133	89.01 291

TR-MVS		77.44 262	76.18 269	81.20 256	88.24 188	63.24 273	84.61 276	86.40 293	67.55 303	77.81 214	86.48 288	54.10 276	93.15 192	57.75 351	82.72 258	87.20 341

CDS-MVSNet		79.07 219	77.70 234	83.17 191	87.60 223	68.23 137	84.40 285	86.20 297	67.49 304	76.36 250	86.54 286	61.54 197	90.79 293	61.86 312	87.33 171	90.49 232
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
fmvsm_l_conf0.5_n_a		84.13 89	84.16 90	84.06 152	85.38 291	68.40 129	88.34 152	86.85 284	67.48 305	87.48 51	93.40 77	70.89 69	91.61 257	88.38 36	89.22 138	92.16 174

mvs_anonymous		79.42 208	79.11 197	80.34 277	84.45 316	57.97 346	82.59 322	87.62 265	67.40 306	76.17 257	88.56 224	68.47 104	89.59 314	70.65 229	86.05 196	93.47 105

viewmambaseed2359dif		80.41 183	79.84 175	82.12 231	82.95 357	62.50 289	83.39 308	88.06 252	67.11 307	80.98 152	90.31 168	66.20 135	91.01 289	74.62 183	84.90 215	92.86 139

mvs5depth		69.45 367	67.45 378	75.46 359	73.93 435	55.83 381	79.19 370	83.23 339	66.89 308	71.63 336	83.32 360	33.69 433	85.09 375	59.81 329	55.34 443	85.46 377

IU-MVS					95.30 2	71.25 61		92.95 56	66.81 309	92.39 6				88.94 27	96.63 4	94.85 21

baseline2		75.70 293	73.83 306	81.30 252	83.26 343	61.79 302	82.57 323	80.65 373	66.81 309	66.88 387	83.42 359	57.86 242	92.19 236	63.47 293	79.57 294	89.91 262

miper_lstm_enhance		74.11 313	73.11 315	77.13 343	80.11 399	59.62 329	72.23 423	86.92 283	66.76 311	70.40 346	82.92 368	56.93 253	82.92 393	69.06 248	72.63 385	88.87 298

OpenMVS	72.83 10	79.77 198	78.33 214	84.09 147	85.17 296	69.91 89	90.57 64	90.97 143	66.70 312	72.17 330	91.91 111	54.70 271	93.96 140	61.81 313	90.95 107	88.41 315

test-LLR		72.94 333	72.43 322	74.48 370	81.35 385	58.04 344	78.38 382	77.46 406	66.66 313	69.95 355	79.00 413	48.06 347	79.24 412	66.13 272	84.83 216	86.15 364

test20.03		67.45 382	66.95 383	68.94 412	75.48 430	44.84 449	77.50 393	77.67 404	66.66 313	63.01 418	83.80 348	47.02 353	78.40 416	42.53 437	68.86 408	83.58 404

test0.0.03 1		68.00 380	67.69 373	68.90 413	77.55 419	47.43 436	75.70 406	72.95 432	66.66 313	66.56 392	82.29 379	48.06 347	75.87 435	44.97 430	74.51 369	83.41 405

Syy-MVS		68.05 379	67.85 368	68.67 416	84.68 310	40.97 459	78.62 379	73.08 430	66.65 316	66.74 390	79.46 408	52.11 298	82.30 397	32.89 451	76.38 340	82.75 414

myMVS_eth3d		67.02 386	66.29 386	69.21 411	84.68 310	42.58 454	78.62 379	73.08 430	66.65 316	66.74 390	79.46 408	31.53 438	82.30 397	39.43 443	76.38 340	82.75 414

QAPM		80.88 163	79.50 186	85.03 100	88.01 202	68.97 110	91.59 46	92.00 101	66.63 318	75.15 285	92.16 106	57.70 243	95.45 71	63.52 292	88.76 147	90.66 224

XXY-MVS		75.41 299	75.56 277	74.96 364	83.59 336	57.82 350	80.59 349	83.87 329	66.54 319	74.93 292	88.31 230	63.24 165	80.09 410	62.16 308	76.85 329	86.97 350

OurMVSNet-221017-0		74.26 310	72.42 323	79.80 289	83.76 331	59.59 330	85.92 239	86.64 288	66.39 320	66.96 386	87.58 250	39.46 410	91.60 258	65.76 278	69.27 404	88.22 318

SCA		74.22 311	72.33 324	79.91 286	84.05 324	62.17 296	79.96 361	79.29 394	66.30 321	72.38 327	80.13 401	51.95 302	88.60 335	59.25 334	77.67 320	88.96 295

testgi		66.67 389	66.53 385	67.08 423	75.62 429	41.69 458	75.93 402	76.50 415	66.11 322	65.20 407	86.59 282	35.72 429	74.71 442	43.71 431	73.38 381	84.84 389

HY-MVS	69.67 12	77.95 249	77.15 247	80.36 276	87.57 227	60.21 324	83.37 310	87.78 262	66.11 322	75.37 274	87.06 269	63.27 163	90.48 300	61.38 317	82.43 261	90.40 236

EG-PatchMatch MVS		74.04 314	71.82 328	80.71 269	84.92 304	67.42 164	85.86 241	88.08 250	66.04 324	64.22 411	83.85 346	35.10 430	92.56 218	57.44 353	80.83 279	82.16 420

CNLPA		78.08 244	76.79 256	81.97 237	90.40 105	71.07 67	87.59 178	84.55 318	66.03 325	72.38 327	89.64 188	57.56 245	86.04 364	59.61 331	83.35 248	88.79 302

Anonymous20240529		80.19 193	78.89 202	84.10 143	90.60 100	64.75 232	88.95 121	90.90 145	65.97 326	80.59 161	91.17 142	49.97 328	93.73 160	69.16 247	82.70 259	93.81 82

TAPA-MVS	73.13 9	79.15 216	77.94 222	82.79 215	89.59 126	62.99 282	88.16 159	91.51 127	65.77 327	77.14 233	91.09 144	60.91 212	93.21 185	50.26 400	87.05 177	92.17 173
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MSDG		73.36 325	70.99 339	80.49 274	84.51 315	65.80 202	80.71 347	86.13 299	65.70 328	65.46 402	83.74 350	44.60 378	90.91 291	51.13 393	76.89 327	84.74 390

anonymousdsp		78.60 231	77.15 247	82.98 203	80.51 395	67.08 177	87.24 192	89.53 194	65.66 329	75.16 284	87.19 264	52.52 289	92.25 234	77.17 150	79.34 299	89.61 273

test_0402		72.79 334	70.44 345	79.84 288	88.13 194	65.99 196	85.93 238	84.29 322	65.57 330	67.40 382	85.49 310	46.92 354	92.61 214	35.88 448	74.38 370	80.94 427

UBG		73.08 330	72.27 325	75.51 357	88.02 200	51.29 423	78.35 385	77.38 409	65.52 331	73.87 307	82.36 376	45.55 372	86.48 359	55.02 371	84.39 227	88.75 304

miper_enhance_ethall		77.87 252	76.86 253	80.92 265	81.65 377	61.38 306	82.68 321	88.98 225	65.52 331	75.47 267	82.30 378	65.76 143	92.00 243	72.95 202	76.39 337	89.39 279

WBMVS		73.43 322	72.81 318	75.28 361	87.91 205	50.99 425	78.59 381	81.31 368	65.51 333	74.47 300	84.83 326	46.39 359	86.68 356	58.41 344	77.86 315	88.17 320

UnsupCasMVSNet_eth		67.33 383	65.99 387	71.37 399	73.48 440	51.47 421	75.16 410	85.19 309	65.20 334	60.78 426	80.93 393	42.35 393	77.20 422	57.12 356	53.69 445	85.44 378

WTY-MVS		75.65 294	75.68 274	75.57 355	86.40 266	56.82 364	77.92 391	82.40 354	65.10 335	76.18 255	87.72 246	63.13 171	80.90 407	60.31 325	81.96 266	89.00 293

thisisatest0515		77.33 265	75.38 282	83.18 190	85.27 295	63.80 254	82.11 327	83.27 338	65.06 336	75.91 259	83.84 347	49.54 333	94.27 127	67.24 265	86.19 193	91.48 195

MVP-Stereo		76.12 287	74.46 297	81.13 259	85.37 292	69.79 91	84.42 284	87.95 256	65.03 337	67.46 379	85.33 314	53.28 286	91.73 255	58.01 349	83.27 250	81.85 422
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Anonymous20231211		78.97 222	77.69 235	82.81 211	90.54 102	64.29 244	90.11 78	91.51 127	65.01 338	76.16 258	88.13 240	50.56 320	93.03 202	69.68 242	77.56 321	91.11 204

pmmvs6		74.69 306	73.39 310	78.61 311	81.38 384	57.48 356	86.64 216	87.95 256	64.99 339	70.18 349	86.61 281	50.43 322	89.52 315	62.12 309	70.18 401	88.83 300

PAPM		77.68 258	76.40 267	81.51 245	87.29 237	61.85 300	83.78 297	89.59 192	64.74 340	71.23 340	88.70 217	62.59 177	93.66 161	52.66 384	87.03 178	89.01 291

MIMVSNet		70.69 353	69.30 352	74.88 366	84.52 314	56.35 375	75.87 405	79.42 391	64.59 341	67.76 374	82.41 375	41.10 403	81.54 402	46.64 421	81.34 271	86.75 355

tpm		72.37 337	71.71 329	74.35 372	82.19 371	52.00 413	79.22 369	77.29 410	64.56 342	72.95 319	83.68 354	51.35 310	83.26 392	58.33 346	75.80 346	87.81 326

MDA-MVSNet-bldmvs		66.68 388	63.66 398	75.75 352	79.28 412	60.56 318	73.92 419	78.35 401	64.43 343	50.13 451	79.87 405	44.02 384	83.67 386	46.10 424	56.86 437	83.03 411

MIMVSNet1		68.58 374	66.78 384	73.98 377	80.07 400	51.82 417	80.77 344	84.37 319	64.40 344	59.75 432	82.16 381	36.47 426	83.63 387	42.73 435	70.33 400	86.48 359

D2MVS		74.82 305	73.21 313	79.64 294	79.81 404	62.56 288	80.34 354	87.35 271	64.37 345	68.86 366	82.66 373	46.37 361	90.10 304	67.91 258	81.24 273	86.25 361

PLC	70.83 11	78.05 246	76.37 268	83.08 196	91.88 79	67.80 152	88.19 157	89.46 196	64.33 346	69.87 357	88.38 228	53.66 281	93.58 162	58.86 339	82.73 257	87.86 325
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PatchmatchNet		73.12 329	71.33 335	78.49 318	83.18 347	60.85 313	79.63 363	78.57 399	64.13 347	71.73 334	79.81 406	51.20 313	85.97 365	57.40 354	76.36 342	88.66 307
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
mamv4		76.81 274	78.23 218	72.54 392	86.12 273	65.75 205	78.76 377	82.07 358	64.12 348	72.97 318	91.02 149	67.97 111	68.08 457	83.04 84	78.02 314	83.80 402

KD-MVS_2432*1600		66.22 393	63.89 396	73.21 383	75.47 431	53.42 405	70.76 430	84.35 320	64.10 349	66.52 394	78.52 417	34.55 431	84.98 376	50.40 396	50.33 450	81.23 425

miper_refine_blended		66.22 393	63.89 396	73.21 383	75.47 431	53.42 405	70.76 430	84.35 320	64.10 349	66.52 394	78.52 417	34.55 431	84.98 376	50.40 396	50.33 450	81.23 425

tpmvs		71.09 348	69.29 353	76.49 347	82.04 372	56.04 378	78.92 375	81.37 367	64.05 351	67.18 384	78.28 419	49.74 332	89.77 310	49.67 403	72.37 386	83.67 403

F-COLMAP		76.38 285	74.33 299	82.50 225	89.28 145	66.95 182	88.41 147	89.03 222	64.05 351	66.83 388	88.61 221	46.78 357	92.89 205	57.48 352	78.55 304	87.67 328

DP-MVS		76.78 275	74.57 293	83.42 179	93.29 48	69.46 100	88.55 143	83.70 330	63.98 353	70.20 348	88.89 213	54.01 279	94.80 107	46.66 419	81.88 268	86.01 368

原ACMM1				84.35 128	93.01 62	68.79 113		92.44 78	63.96 354	81.09 150	91.57 127	66.06 138	95.45 71	67.19 266	94.82 46	88.81 301

PM-MVS		66.41 391	64.14 394	73.20 385	73.92 436	56.45 370	78.97 374	64.96 452	63.88 355	64.72 408	80.24 400	19.84 457	83.44 390	66.24 271	64.52 421	79.71 433

FE-MVSNET		67.25 385	65.33 389	73.02 387	75.86 426	52.54 411	80.26 357	80.56 375	63.80 356	60.39 427	79.70 407	41.41 401	84.66 381	43.34 433	62.62 426	81.86 421

UWE-MVS		72.13 341	71.49 331	74.03 376	86.66 260	47.70 435	81.40 337	76.89 414	63.60 357	75.59 264	84.22 341	39.94 409	85.62 369	48.98 407	86.13 195	88.77 303

jason		81.39 155	80.29 162	84.70 117	86.63 261	69.90 90	85.95 237	86.77 285	63.24 358	81.07 151	89.47 194	61.08 210	92.15 237	78.33 136	90.07 123	92.05 177
jason: jason.
KD-MVS_self_test		68.81 371	67.59 376	72.46 393	74.29 434	45.45 443	77.93 390	87.00 279	63.12 359	63.99 414	78.99 415	42.32 394	84.77 379	56.55 365	64.09 422	87.16 344

gg-mvs-nofinetune		69.95 363	67.96 366	75.94 350	83.07 350	54.51 397	77.23 396	70.29 436	63.11 360	70.32 347	62.33 450	43.62 386	88.69 333	53.88 378	87.76 164	84.62 392

tpmrst		72.39 335	72.13 326	73.18 386	80.54 394	49.91 430	79.91 362	79.08 396	63.11 360	71.69 335	79.95 403	55.32 263	82.77 395	65.66 279	73.89 374	86.87 351

PCF-MVS	73.52 7	80.38 185	78.84 203	85.01 101	87.71 218	68.99 109	83.65 301	91.46 131	63.00 362	77.77 216	90.28 169	66.10 136	95.09 94	61.40 316	88.22 157	90.94 213
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
COLMAP_ROB	66.92 17	73.01 331	70.41 346	80.81 267	87.13 241	65.63 206	88.30 154	84.19 325	62.96 363	63.80 416	87.69 248	38.04 420	92.56 218	46.66 419	74.91 365	84.24 395
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Patchmatch-RL test		70.24 359	67.78 372	77.61 335	77.43 420	59.57 331	71.16 427	70.33 435	62.94 364	68.65 368	72.77 441	50.62 319	85.49 371	69.58 243	66.58 414	87.77 327

lupinMVS		81.39 155	80.27 163	84.76 115	87.35 228	70.21 82	85.55 250	86.41 292	62.85 365	81.32 145	88.61 221	61.68 194	92.24 235	78.41 135	90.26 118	91.83 180

test_vis1_n_1920		75.52 296	75.78 272	74.75 369	79.84 403	57.44 357	83.26 312	85.52 306	62.83 366	79.34 181	86.17 295	45.10 376	79.71 411	78.75 130	81.21 274	87.10 348

EPMVS		69.02 370	68.16 362	71.59 397	79.61 408	49.80 432	77.40 394	66.93 446	62.82 367	70.01 352	79.05 411	45.79 369	77.86 420	56.58 364	75.26 361	87.13 345

PatchMatch-RL		72.38 336	70.90 340	76.80 346	88.60 175	67.38 167	79.53 364	76.17 418	62.75 368	69.36 362	82.00 384	45.51 373	84.89 378	53.62 379	80.58 283	78.12 436

gm-plane-assit					81.40 383	53.83 402			62.72 369		80.94 391		92.39 227	63.40 295

FMVSNet5		69.50 366	67.96 366	74.15 375	82.97 356	55.35 388	80.01 360	82.12 357	62.56 370	63.02 417	81.53 385	36.92 423	81.92 400	48.42 409	74.06 372	85.17 384

sss		73.60 320	73.64 308	73.51 381	82.80 359	55.01 392	76.12 401	81.69 362	62.47 371	74.68 296	85.85 301	57.32 248	78.11 418	60.86 321	80.93 276	87.39 335

WB-MVSnew		71.96 343	71.65 330	72.89 388	84.67 313	51.88 416	82.29 325	77.57 405	62.31 372	73.67 310	83.00 366	53.49 284	81.10 406	45.75 426	82.13 264	85.70 374

AllTest		70.96 349	68.09 364	79.58 295	85.15 298	63.62 257	84.58 277	79.83 387	62.31 372	60.32 429	86.73 272	32.02 435	88.96 329	50.28 398	71.57 394	86.15 364

TestCases				79.58 295	85.15 298	63.62 257		79.83 387	62.31 372	60.32 429	86.73 272	32.02 435	88.96 329	50.28 398	71.57 394	86.15 364

1112_ss		77.40 264	76.43 265	80.32 278	89.11 156	60.41 321	83.65 301	87.72 264	62.13 375	73.05 317	86.72 274	62.58 178	89.97 307	62.11 310	80.80 280	90.59 228

PVSNet	64.34 18	72.08 342	70.87 341	75.69 353	86.21 269	56.44 371	74.37 417	80.73 372	62.06 376	70.17 350	82.23 380	42.86 391	83.31 391	54.77 373	84.45 225	87.32 338

UWE-MVS-28		65.32 396	64.93 390	66.49 424	78.70 415	38.55 461	77.86 392	64.39 453	62.00 377	64.13 412	83.60 355	41.44 400	76.00 433	31.39 453	80.89 277	84.92 387

LS3D		76.95 272	74.82 290	83.37 182	90.45 103	67.36 168	89.15 114	86.94 281	61.87 378	69.52 360	90.61 161	51.71 308	94.53 118	46.38 422	86.71 184	88.21 319

CostFormer		75.24 302	73.90 304	79.27 300	82.65 364	58.27 341	80.80 342	82.73 352	61.57 379	75.33 279	83.13 364	55.52 262	91.07 288	64.98 284	78.34 312	88.45 313

new-patchmatchnet		61.73 406	61.73 407	61.70 430	72.74 446	24.50 473	69.16 437	78.03 402	61.40 380	56.72 441	75.53 435	38.42 417	76.48 428	45.95 425	57.67 436	84.13 397

ANet_high		50.57 424	46.10 428	63.99 427	48.67 472	39.13 460	70.99 429	80.85 370	61.39 381	31.18 461	57.70 457	17.02 460	73.65 448	31.22 454	15.89 469	79.18 434

MS-PatchMatch		73.83 317	72.67 319	77.30 341	83.87 328	66.02 193	81.82 328	84.66 316	61.37 382	68.61 369	82.82 371	47.29 350	88.21 339	59.27 333	84.32 228	77.68 437

USDC		70.33 358	68.37 359	76.21 349	80.60 393	56.23 376	79.19 370	86.49 291	60.89 383	61.29 424	85.47 311	31.78 437	89.47 317	53.37 381	76.21 343	82.94 413

cascas		76.72 276	74.64 292	82.99 201	85.78 280	65.88 199	82.33 324	89.21 214	60.85 384	72.74 320	81.02 389	47.28 351	93.75 158	67.48 262	85.02 213	89.34 281

sc_t1		72.19 340	69.51 351	80.23 280	84.81 306	61.09 309	84.68 272	80.22 384	60.70 385	71.27 339	83.58 356	36.59 425	89.24 321	60.41 323	63.31 424	90.37 237

MDTV_nov1_ep13			69.97 350		83.18 347	53.48 404	77.10 398	80.18 386	60.45 386	69.33 363	80.44 395	48.89 345	86.90 354	51.60 389	78.51 306

TinyColmap		67.30 384	64.81 391	74.76 368	81.92 375	56.68 368	80.29 355	81.49 365	60.33 387	56.27 443	83.22 361	24.77 449	87.66 348	45.52 427	69.47 403	79.95 432

test-mter		71.41 345	70.39 347	74.48 370	81.35 385	58.04 344	78.38 382	77.46 406	60.32 388	69.95 355	79.00 413	36.08 428	79.24 412	66.13 272	84.83 216	86.15 364

1314		76.53 278	75.30 285	80.21 281	83.93 326	62.32 294	84.66 273	88.81 231	60.23 389	70.16 351	84.07 344	55.30 264	90.73 297	67.37 263	83.21 251	87.59 332

PatchT		68.46 377	67.85 368	70.29 407	80.70 392	43.93 451	72.47 422	74.88 422	60.15 390	70.55 343	76.57 428	49.94 329	81.59 401	50.58 394	74.83 366	85.34 379

无先验							87.48 180	88.98 225	60.00 391				94.12 136	67.28 264		88.97 294

CR-MVSNet		73.37 323	71.27 336	79.67 293	81.32 387	65.19 217	75.92 403	80.30 382	59.92 392	72.73 321	81.19 386	52.50 290	86.69 355	59.84 328	77.71 317	87.11 346

TDRefinement		67.49 381	64.34 393	76.92 344	73.47 441	61.07 310	84.86 269	82.98 347	59.77 393	58.30 436	85.13 320	26.06 445	87.89 344	47.92 416	60.59 433	81.81 423

dp		66.80 387	65.43 388	70.90 406	79.74 407	48.82 434	75.12 412	74.77 423	59.61 394	64.08 413	77.23 425	42.89 390	80.72 408	48.86 408	66.58 414	83.16 408

our_test_3		69.14 369	67.00 382	75.57 355	79.80 405	58.80 335	77.96 389	77.81 403	59.55 395	62.90 420	78.25 420	47.43 349	83.97 384	51.71 388	67.58 411	83.93 400

Test_1112_low_res		76.40 284	75.44 279	79.27 300	89.28 145	58.09 342	81.69 331	87.07 278	59.53 396	72.48 325	86.67 279	61.30 204	89.33 318	60.81 322	80.15 289	90.41 235

pmmvs4		74.03 316	71.91 327	80.39 275	81.96 373	68.32 131	81.45 335	82.14 356	59.32 397	69.87 357	85.13 320	52.40 292	88.13 341	60.21 326	74.74 367	84.73 391

testdata				79.97 285	90.90 94	64.21 245		84.71 315	59.27 398	85.40 70	92.91 89	62.02 189	89.08 325	68.95 249	91.37 100	86.63 358

WB-MVS		54.94 414	54.72 415	55.60 440	73.50 439	20.90 474	74.27 418	61.19 457	59.16 399	50.61 449	74.15 437	47.19 352	75.78 436	17.31 465	35.07 459	70.12 447

ppachtmachnet_test		70.04 362	67.34 380	78.14 323	79.80 405	61.13 307	79.19 370	80.59 374	59.16 399	65.27 404	79.29 410	46.75 358	87.29 351	49.33 405	66.72 412	86.00 370

RPSCF		73.23 328	71.46 332	78.54 315	82.50 366	59.85 326	82.18 326	82.84 351	58.96 401	71.15 342	89.41 200	45.48 375	84.77 379	58.82 340	71.83 392	91.02 210

pmmvs-eth3d		70.50 356	67.83 370	78.52 317	77.37 421	66.18 191	81.82 328	81.51 364	58.90 402	63.90 415	80.42 396	42.69 392	86.28 361	58.56 342	65.30 419	83.11 409

tt0320-xc		70.11 361	67.45 378	78.07 326	85.33 293	59.51 332	83.28 311	78.96 397	58.77 403	67.10 385	80.28 399	36.73 424	87.42 350	56.83 362	59.77 435	87.29 339

OpenMVS_ROB	64.09 19	70.56 355	68.19 361	77.65 334	80.26 396	59.41 333	85.01 265	82.96 348	58.76 404	65.43 403	82.33 377	37.63 422	91.23 280	45.34 429	76.03 344	82.32 417

114514_t		80.68 174	79.51 185	84.20 140	94.09 38	67.27 172	89.64 90	91.11 140	58.75 405	74.08 304	90.72 155	58.10 239	95.04 95	69.70 241	89.42 135	90.30 241

Patchmtry		70.74 352	69.16 355	75.49 358	80.72 391	54.07 400	74.94 414	80.30 382	58.34 406	70.01 352	81.19 386	52.50 290	86.54 357	53.37 381	71.09 397	85.87 373

test_cas_vis1_n_1920		73.76 318	73.74 307	73.81 379	75.90 425	59.77 327	80.51 350	82.40 354	58.30 407	81.62 142	85.69 303	44.35 382	76.41 429	76.29 162	78.61 303	85.23 381

Anonymous20240521		68.80 372	67.22 381	73.55 380	74.33 433	54.11 399	83.18 313	85.61 305	58.15 408	61.68 423	80.94 391	30.71 440	81.27 405	57.00 359	73.34 382	85.28 380

tt0320		70.49 357	68.03 365	77.89 328	84.78 307	59.12 334	83.55 305	80.44 379	58.13 409	67.43 381	80.41 397	39.26 412	87.54 349	55.12 370	63.18 425	86.99 349

旧先验2							86.56 219		58.10 410	87.04 57			88.98 327	74.07 190

JIA-IIPM		66.32 392	62.82 404	76.82 345	77.09 422	61.72 303	65.34 450	75.38 419	58.04 411	64.51 409	62.32 451	42.05 398	86.51 358	51.45 391	69.22 405	82.21 418

pmmvs5		71.55 344	70.20 349	75.61 354	77.83 418	56.39 372	81.74 330	80.89 369	57.76 412	67.46 379	84.49 330	49.26 339	85.32 374	57.08 357	75.29 360	85.11 385

TESTMET0.1,1		69.89 364	69.00 356	72.55 391	79.27 413	56.85 363	78.38 382	74.71 425	57.64 413	68.09 373	77.19 426	37.75 421	76.70 425	63.92 291	84.09 231	84.10 398

RPMNet		73.51 321	70.49 344	82.58 224	81.32 387	65.19 217	75.92 403	92.27 85	57.60 414	72.73 321	76.45 429	52.30 293	95.43 73	48.14 414	77.71 317	87.11 346

SSC-MVS		53.88 417	53.59 417	54.75 442	72.87 445	19.59 475	73.84 420	60.53 459	57.58 415	49.18 453	73.45 440	46.34 363	75.47 439	16.20 468	32.28 461	69.20 448

新几何1				83.42 179	93.13 56	70.71 76		85.48 307	57.43 416	81.80 137	91.98 110	63.28 162	92.27 233	64.60 287	92.99 72	87.27 340

YYNet1		65.03 397	62.91 402	71.38 398	75.85 427	56.60 369	69.12 438	74.66 426	57.28 417	54.12 445	77.87 422	45.85 368	74.48 443	49.95 401	61.52 430	83.05 410

MDA-MVSNet_test_wron		65.03 397	62.92 401	71.37 399	75.93 424	56.73 365	69.09 439	74.73 424	57.28 417	54.03 446	77.89 421	45.88 367	74.39 444	49.89 402	61.55 429	82.99 412

Anonymous20231206		68.60 373	67.80 371	71.02 404	80.23 398	50.75 427	78.30 386	80.47 377	56.79 419	66.11 400	82.63 374	46.35 362	78.95 414	43.62 432	75.70 347	83.36 406

tpm2		73.26 327	71.46 332	78.63 310	83.34 341	56.71 367	80.65 348	80.40 381	56.63 420	73.55 311	82.02 383	51.80 306	91.24 279	56.35 366	78.42 310	87.95 322

CHOSEN 1792x2688		77.63 260	75.69 273	83.44 178	89.98 118	68.58 125	78.70 378	87.50 268	56.38 421	75.80 262	86.84 270	58.67 235	91.40 274	61.58 315	85.75 205	90.34 238

HyFIR lowres test		77.53 261	75.40 281	83.94 164	89.59 126	66.62 184	80.36 353	88.64 242	56.29 422	76.45 247	85.17 319	57.64 244	93.28 178	61.34 318	83.10 253	91.91 179

PVSNet_0	57.27 20	61.67 407	59.27 410	68.85 414	79.61 408	57.44 357	68.01 440	73.44 429	55.93 423	58.54 435	70.41 446	44.58 379	77.55 421	47.01 418	35.91 458	71.55 446

UnsupCasMVSNet_bld		63.70 402	61.53 408	70.21 408	73.69 438	51.39 422	72.82 421	81.89 359	55.63 424	57.81 438	71.80 443	38.67 416	78.61 415	49.26 406	52.21 448	80.63 429

MDTV_nov1_ep13_2view						37.79 462	75.16 410		55.10 425	66.53 393		49.34 337		53.98 377		87.94 323

MVS		78.19 242	76.99 251	81.78 239	85.66 282	66.99 178	84.66 273	90.47 158	55.08 426	72.02 332	85.27 315	63.83 159	94.11 137	66.10 274	89.80 128	84.24 395

test222					91.50 82	68.26 133	84.16 291	83.20 342	54.63 427	79.74 171	91.63 123	58.97 232			91.42 98	86.77 354

dongtai		45.42 428	45.38 429	45.55 446	73.36 442	26.85 470	67.72 441	34.19 472	54.15 428	49.65 452	56.41 459	25.43 446	62.94 462	19.45 463	28.09 463	46.86 462

CHOSEN 280x420		66.51 390	64.71 392	71.90 395	81.45 382	63.52 266	57.98 459	68.95 442	53.57 429	62.59 421	76.70 427	46.22 364	75.29 441	55.25 369	79.68 293	76.88 439

ADS-MVSNet2		66.20 395	63.33 399	74.82 367	79.92 401	58.75 336	67.55 442	75.19 420	53.37 430	65.25 405	75.86 432	42.32 394	80.53 409	41.57 438	68.91 406	85.18 382

ADS-MVSNet		64.36 400	62.88 403	68.78 415	79.92 401	47.17 439	67.55 442	71.18 434	53.37 430	65.25 405	75.86 432	42.32 394	73.99 446	41.57 438	68.91 406	85.18 382

LF4IMVS		64.02 401	62.19 405	69.50 410	70.90 449	53.29 408	76.13 400	77.18 411	52.65 432	58.59 434	80.98 390	23.55 452	76.52 427	53.06 383	66.66 413	78.68 435

tpm cat1		70.57 354	68.31 360	77.35 340	82.41 369	57.95 347	78.08 387	80.22 384	52.04 433	68.54 370	77.66 424	52.00 301	87.84 345	51.77 387	72.07 391	86.25 361

test_vis1_n		69.85 365	69.21 354	71.77 396	72.66 447	55.27 390	81.48 334	76.21 417	52.03 434	75.30 280	83.20 363	28.97 442	76.22 431	74.60 184	78.41 311	83.81 401

Patchmatch-test		64.82 399	63.24 400	69.57 409	79.42 411	49.82 431	63.49 456	69.05 441	51.98 435	59.95 431	80.13 401	50.91 315	70.98 450	40.66 440	73.57 377	87.90 324

N_pmnet		52.79 420	53.26 418	51.40 444	78.99 414	7.68 478	69.52 434	3.89 477	51.63 436	57.01 440	74.98 436	40.83 405	65.96 459	37.78 445	64.67 420	80.56 431

test_fmvs1_n		70.86 351	70.24 348	72.73 390	72.51 448	55.28 389	81.27 338	79.71 389	51.49 437	78.73 188	84.87 325	27.54 444	77.02 423	76.06 166	79.97 292	85.88 372

test_fmvs1		70.93 350	70.52 343	72.16 394	73.71 437	55.05 391	80.82 341	78.77 398	51.21 438	78.58 193	84.41 333	31.20 439	76.94 424	75.88 170	80.12 291	84.47 393

PMMVS		69.34 368	68.67 357	71.35 401	75.67 428	62.03 297	75.17 409	73.46 428	50.00 439	68.68 367	79.05 411	52.07 300	78.13 417	61.16 319	82.77 256	73.90 443

test_fmvs2		68.35 378	67.48 377	70.98 405	69.50 451	51.95 414	80.05 359	76.38 416	49.33 440	74.65 297	84.38 334	23.30 453	75.40 440	74.51 185	75.17 363	85.60 375

ttmdpeth		59.91 409	57.10 413	68.34 418	67.13 455	46.65 442	74.64 415	67.41 445	48.30 441	62.52 422	85.04 324	20.40 455	75.93 434	42.55 436	45.90 456	82.44 416

CMPMVS	51.72 21	70.19 360	68.16 362	76.28 348	73.15 444	57.55 355	79.47 365	83.92 327	48.02 442	56.48 442	84.81 327	43.13 389	86.42 360	62.67 302	81.81 269	84.89 388
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
mvsany_test1		62.30 405	61.26 409	65.41 426	69.52 450	54.86 393	66.86 444	49.78 466	46.65 443	68.50 371	83.21 362	49.15 340	66.28 458	56.93 360	60.77 431	75.11 442

kuosan		39.70 432	40.40 433	37.58 449	64.52 458	26.98 468	65.62 449	33.02 473	46.12 444	42.79 456	48.99 462	24.10 451	46.56 470	12.16 471	26.30 464	39.20 463

test_fmvs3		63.36 403	61.82 406	67.98 420	62.51 460	46.96 441	77.37 395	74.03 427	45.24 445	67.50 378	78.79 416	12.16 465	72.98 449	72.77 205	66.02 416	83.99 399

CVMVSNet		72.99 332	72.58 321	74.25 374	84.28 317	50.85 426	86.41 223	83.45 336	44.56 446	73.23 315	87.54 254	49.38 336	85.70 367	65.90 276	78.44 307	86.19 363

test_vis1_rt		60.28 408	58.42 411	65.84 425	67.25 454	55.60 385	70.44 432	60.94 458	44.33 447	59.00 433	66.64 448	24.91 448	68.67 455	62.80 298	69.48 402	73.25 444

mvsany_test3		53.99 416	51.45 421	61.61 431	55.51 465	44.74 450	63.52 455	45.41 470	43.69 448	58.11 437	76.45 429	17.99 458	63.76 461	54.77 373	47.59 452	76.34 440

EU-MVSNet		68.53 376	67.61 375	71.31 402	78.51 417	47.01 440	84.47 279	84.27 323	42.27 449	66.44 397	84.79 328	40.44 407	83.76 385	58.76 341	68.54 409	83.17 407

FPMVS		53.68 418	51.64 420	59.81 433	65.08 457	51.03 424	69.48 435	69.58 439	41.46 450	40.67 457	72.32 442	16.46 461	70.00 454	24.24 461	65.42 418	58.40 457

pmmvs3		57.79 411	54.26 416	68.37 417	64.02 459	56.72 366	75.12 412	65.17 450	40.20 451	52.93 447	69.86 447	20.36 456	75.48 438	45.45 428	55.25 444	72.90 445

new_pmnet		50.91 423	50.29 423	52.78 443	68.58 452	34.94 465	63.71 454	56.63 463	39.73 452	44.95 454	65.47 449	21.93 454	58.48 463	34.98 449	56.62 438	64.92 451

MVS-HIRNet		59.14 410	57.67 412	63.57 428	81.65 377	43.50 452	71.73 424	65.06 451	39.59 453	51.43 448	57.73 456	38.34 418	82.58 396	39.53 441	73.95 373	64.62 452

MVStest1		56.63 413	52.76 419	68.25 419	61.67 461	53.25 409	71.67 425	68.90 443	38.59 454	50.59 450	83.05 365	25.08 447	70.66 451	36.76 447	38.56 457	80.83 428

PMMVS2		40.82 431	38.86 435	46.69 445	53.84 467	16.45 476	48.61 462	49.92 465	37.49 455	31.67 460	60.97 453	8.14 471	56.42 465	28.42 456	30.72 462	67.19 450

test_vis3_rt		49.26 425	47.02 427	56.00 437	54.30 466	45.27 447	66.76 446	48.08 467	36.83 456	44.38 455	53.20 460	7.17 472	64.07 460	56.77 363	55.66 440	58.65 456

test_f		52.09 421	50.82 422	55.90 438	53.82 468	42.31 457	59.42 458	58.31 462	36.45 457	56.12 444	70.96 445	12.18 464	57.79 464	53.51 380	56.57 439	67.60 449

LCM-MVSNet		54.25 415	49.68 425	67.97 421	53.73 469	45.28 446	66.85 445	80.78 371	35.96 458	39.45 459	62.23 452	8.70 469	78.06 419	48.24 413	51.20 449	80.57 430

APD_test1		53.31 419	49.93 424	63.42 429	65.68 456	50.13 429	71.59 426	66.90 447	34.43 459	40.58 458	71.56 444	8.65 470	76.27 430	34.64 450	55.36 442	63.86 453

PMVS	37.38 22	44.16 430	40.28 434	55.82 439	40.82 474	42.54 456	65.12 451	63.99 454	34.43 459	24.48 465	57.12 458	3.92 475	76.17 432	17.10 466	55.52 441	48.75 460
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		45.18 429	41.86 432	55.16 441	77.03 423	51.52 420	32.50 465	80.52 376	32.46 461	27.12 464	35.02 465	9.52 468	75.50 437	22.31 462	60.21 434	38.45 464
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DSMNet-mixed		57.77 412	56.90 414	60.38 432	67.70 453	35.61 463	69.18 436	53.97 464	32.30 462	57.49 439	79.88 404	40.39 408	68.57 456	38.78 444	72.37 386	76.97 438

testf1		45.72 426	41.96 430	57.00 435	56.90 463	45.32 444	66.14 447	59.26 460	26.19 463	30.89 462	60.96 454	4.14 473	70.64 452	26.39 459	46.73 454	55.04 458

APD_test2		45.72 426	41.96 430	57.00 435	56.90 463	45.32 444	66.14 447	59.26 460	26.19 463	30.89 462	60.96 454	4.14 473	70.64 452	26.39 459	46.73 454	55.04 458

E-PMN		31.77 433	30.64 436	35.15 450	52.87 470	27.67 467	57.09 460	47.86 468	24.64 465	16.40 470	33.05 466	11.23 466	54.90 466	14.46 469	18.15 467	22.87 466

EMVS		30.81 435	29.65 437	34.27 451	50.96 471	25.95 471	56.58 461	46.80 469	24.01 466	15.53 471	30.68 467	12.47 463	54.43 467	12.81 470	17.05 468	22.43 467

MVE	26.22 23	30.37 436	25.89 440	43.81 447	44.55 473	35.46 464	28.87 466	39.07 471	18.20 467	18.58 469	40.18 464	2.68 476	47.37 469	17.07 467	23.78 466	48.60 461
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				27.40 452	40.17 475	26.90 469		24.59 476	17.44 468	23.95 466	48.61 463	9.77 467	26.48 471	18.06 464	24.47 465	28.83 465

wuyk23d		16.82 439	15.94 442	19.46 453	58.74 462	31.45 466	39.22 463	3.74 478	6.84 469	6.04 472	2.70 472	1.27 477	24.29 472	10.54 472	14.40 471	2.63 469

test_method		31.52 434	29.28 438	38.23 448	27.03 476	6.50 479	20.94 467	62.21 456	4.05 470	22.35 468	52.50 461	13.33 462	47.58 468	27.04 458	34.04 460	60.62 454

tmp_tt		18.61 438	21.40 441	10.23 454	4.82 477	10.11 477	34.70 464	30.74 475	1.48 471	23.91 467	26.07 468	28.42 443	13.41 473	27.12 457	15.35 470	7.17 468

EGC-MVSNET		52.07 422	47.05 426	67.14 422	83.51 338	60.71 315	80.50 351	67.75 444	0.07 472	0.43 473	75.85 434	24.26 450	81.54 402	28.82 455	62.25 427	59.16 455

testmvs		6.04 442	8.02 445	0.10 456	0.08 478	0.03 481	69.74 433	0.04 479	0.05 473	0.31 474	1.68 473	0.02 479	0.04 474	0.24 473	0.02 472	0.25 471

test123		6.12 441	8.11 444	0.14 455	0.06 479	0.09 480	71.05 428	0.03 480	0.04 474	0.25 475	1.30 474	0.05 478	0.03 475	0.21 474	0.01 473	0.29 470

mmdepth		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

monomultidepth		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

test_blank		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

uanet_test		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

DCPMVS		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

cdsmvs_eth3d_5k		19.96 437	26.61 439	0.00 457	0.00 480	0.00 482	0.00 468	89.26 210	0.00 475	0.00 476	88.61 221	61.62 196	0.00 476	0.00 475	0.00 474	0.00 472

pcd_1.5k_mvsjas		5.26 443	7.02 446	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	63.15 168	0.00 476	0.00 475	0.00 474	0.00 472

sosnet-low-res		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

sosnet		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

uncertanet		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

Regformer		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

ab-mvs-re		7.23 440	9.64 443	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	86.72 274	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

uanet		0.00 444	0.00 447	0.00 457	0.00 480	0.00 482	0.00 468	0.00 481	0.00 475	0.00 476	0.00 475	0.00 480	0.00 476	0.00 475	0.00 474	0.00 472

WAC-MVS						42.58 454								39.46 442

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 15	96.44 9	94.41 46

No_MVS				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 15	96.44 9	94.41 46

eth-test2					0.00 480

eth-test					0.00 480

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 56	82.45 3	96.87 20	83.77 77	96.48 8	94.88 16

test_0728_SECOND				87.71 32	95.34 1	71.43 60	93.49 10	94.23 3					97.49 4	89.08 22	96.41 12	94.21 58

GSMVS																88.96 295

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs1												51.32 311				88.96 295

sam_mvs												50.01 327

ambc				75.24 362	73.16 443	50.51 428	63.05 457	87.47 269		64.28 410	77.81 423	17.80 459	89.73 312	57.88 350	60.64 432	85.49 376

MTGPA								92.02 99

test_post1							78.90 376				5.43 471	48.81 346	85.44 373	59.25 334

test_post											5.46 470	50.36 323	84.24 382

patchmatchnet-post											74.00 438	51.12 314	88.60 335

GG-mvs-BLEND				75.38 360	81.59 379	55.80 382	79.32 367	69.63 438		67.19 383	73.67 439	43.24 388	88.90 331	50.41 395	84.50 221	81.45 424

MTMP							92.18 35	32.83 474

test9_res														84.90 59	95.70 26	92.87 138

agg_prior2														82.91 86	95.45 29	92.70 143

agg_prior					92.85 64	71.94 52		91.78 115		84.41 90			94.93 97

test_prior4						72.60 34	89.01 119

test_prior				86.33 60	92.61 70	69.59 94		92.97 55					95.48 70			93.91 74

新几何2							86.29 230

旧先验1					91.96 76	65.79 203		86.37 294			93.08 87	69.31 91			92.74 76	88.74 306

原ACMM2							86.86 206

testdata2													91.01 289	62.37 305

segment_acmp												73.08 40

test12				86.80 54	92.63 69	70.70 77		91.79 114		82.71 124		71.67 59	96.16 48		94.50 53	93.54 103

plane_prior7					90.08 112	68.51 127

plane_prior6					89.84 121	68.70 121						60.42 222

plane_prior5								92.44 78					95.38 78	78.71 131	86.32 189	91.33 198

plane_prior4											91.00 150

plane_prior1					89.90 120

n2								0.00 481

nn								0.00 481

door-mid								69.98 437

lessismore_v0				78.97 305	81.01 390	57.15 360		65.99 448		61.16 425	82.82 371	39.12 413	91.34 276	59.67 330	46.92 453	88.43 314

test11								92.23 88

door								69.44 440

HQP5-MVS						66.98 179

BP-MVS														77.47 146

HQP4-MVS										77.24 226			95.11 90			91.03 208

HQP3-MVS								92.19 93							85.99 198

HQP2-MVS												60.17 225

NP-MVS					89.62 125	68.32 131					90.24 171

ACMMP++_ref															81.95 267

ACMMP++															81.25 272

Test By Simon												64.33 154

High-resolution multi-view benchmark