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.

LCM-MVSNet		99.43 1	99.49 1	99.24 2	99.95 1	98.13 2	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 2	97.58 2	99.94 1	99.85 2

LTVRE_ROB	93.87 1	97.93 3	98.16 2	97.26 30	98.81 27	93.86 35	99.07 2	98.98 9	97.01 15	98.92 5	98.78 16	95.22 42	98.61 176	96.85 4	99.77 9	99.31 28
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		97.68 4	97.60 5	97.93 3	99.02 12	95.95 9	98.61 3	98.81 11	97.41 11	97.28 58	98.46 33	94.62 66	98.84 134	94.64 37	99.53 37	98.99 56

DVP-MVS++		95.93 56	96.34 38	94.70 115	96.54 182	86.66 158	98.45 4	98.22 44	93.26 78	97.54 43	97.36 100	93.12 100	99.38 58	93.88 53	98.68 159	98.04 161

FOURS1					99.21 3	94.68 16	98.45 4	98.81 11	97.73 7	98.27 21

UA-Net		97.35 5	97.24 12	97.69 6	98.22 75	93.87 34	98.42 6	98.19 47	96.95 16	95.46 147	99.23 6	93.45 87	99.57 15	95.34 29	99.89 2	99.63 11

OurMVSNet-221017-0		96.80 16	96.75 21	96.96 39	99.03 11	91.85 61	97.98 7	98.01 81	94.15 58	98.93 4	99.07 7	88.07 195	99.57 15	95.86 15	99.69 14	99.46 19

UniMVSNet_ETH3D		97.13 9	97.72 4	95.35 86	99.51 2	87.38 137	97.70 8	97.54 123	98.16 3	98.94 3	99.33 3	97.84 4	99.08 100	90.73 149	99.73 13	99.59 14

tt0805		95.42 80	95.93 62	93.86 155	98.75 31	88.47 120	97.68 9	94.29 278	96.48 24	95.38 150	93.63 294	94.89 59	97.94 242	95.38 27	96.92 278	95.17 320

HPM-MVS		96.81 15	96.62 26	97.36 27	98.89 20	93.53 42	97.51 10	98.44 20	92.35 93	95.95 119	96.41 170	96.71 8	99.42 36	93.99 52	99.36 58	99.13 41
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPP-MVSNet		93.91 143	93.68 152	94.59 124	98.08 83	85.55 188	97.44 11	94.03 283	94.22 57	94.94 178	96.19 190	82.07 270	99.57 15	87.28 237	98.89 128	98.65 106

mvs5depth		95.28 88	95.82 71	93.66 164	96.42 192	83.08 226	97.35 12	99.28 3	96.44 26	96.20 109	99.65 2	84.10 248	98.01 234	94.06 49	98.93 125	99.87 1

LS3D		96.11 51	95.83 69	96.95 40	94.75 286	94.20 23	97.34 13	97.98 84	97.31 12	95.32 155	96.77 146	93.08 102	99.20 87	91.79 124	98.16 210	97.44 222

HPM-MVS_fast		97.01 10	96.89 18	97.39 25	99.12 8	93.92 32	97.16 14	98.17 53	93.11 80	96.48 92	97.36 100	96.92 6	99.34 65	94.31 44	99.38 57	98.92 72

MVSFormer		92.18 198	92.23 190	92.04 227	94.74 287	80.06 265	97.15 15	97.37 134	88.98 183	88.83 333	92.79 316	77.02 313	99.60 10	96.41 9	96.75 285	96.46 270

test_djsdf		96.62 27	96.49 30	97.01 36	98.55 44	91.77 63	97.15 15	97.37 134	88.98 183	98.26 24	98.86 12	93.35 92	99.60 10	96.41 9	99.45 45	99.66 8

IS-MVSNet		94.49 118	94.35 130	94.92 105	98.25 73	86.46 163	97.13 17	94.31 277	96.24 31	96.28 103	96.36 178	82.88 258	99.35 62	88.19 217	99.52 39	98.96 64

Anonymous20231211		96.60 29	97.13 16	95.00 103	97.46 132	86.35 168	97.11 18	98.24 40	97.58 9	98.72 9	98.97 9	93.15 99	99.15 91	93.18 85	99.74 12	99.50 18

anonymousdsp		96.74 21	96.42 33	97.68 8	98.00 92	94.03 29	96.97 19	97.61 117	87.68 215	98.45 19	98.77 17	94.20 77	99.50 22	96.70 6	99.40 55	99.53 16

ACMMP		96.61 28	96.34 38	97.43 22	98.61 37	93.88 33	96.95 20	98.18 49	92.26 96	96.33 97	96.84 144	95.10 48	99.40 49	93.47 70	99.33 65	99.02 53
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
APDe-MVS		96.46 35	96.64 25	95.93 64	97.68 118	89.38 98	96.90 21	98.41 23	92.52 88	97.43 50	97.92 61	95.11 47	99.50 22	94.45 40	99.30 72	98.92 72
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
EGC-MVSNET		80.97 369	75.73 386	96.67 46	98.85 23	94.55 19	96.83 22	96.60 195	2.44 423	5.32 424	98.25 40	92.24 120	98.02 233	91.85 122	99.21 90	97.45 220

v7n		96.82 13	97.31 11	95.33 88	98.54 46	86.81 152	96.83 22	98.07 69	96.59 23	98.46 18	98.43 35	92.91 107	99.52 20	96.25 12	99.76 10	99.65 10

CP-MVS		96.44 38	96.08 53	97.54 15	98.29 68	94.62 18	96.80 24	98.08 66	92.67 86	95.08 173	96.39 175	94.77 62	99.42 36	93.17 86	99.44 48	98.58 118

COLMAP_ROB	91.06 5	96.75 20	96.62 26	97.13 32	98.38 61	94.31 21	96.79 25	98.32 30	96.69 19	96.86 76	97.56 81	95.48 27	98.77 151	90.11 173	99.44 48	98.31 140
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
WR-MVS_H		96.60 29	97.05 17	95.24 94	99.02 12	86.44 164	96.78 26	98.08 66	97.42 10	98.48 17	97.86 65	91.76 134	99.63 8	94.23 46	99.84 3	99.66 8

FE-MVS		89.06 270	88.29 278	91.36 249	94.78 284	79.57 280	96.77 27	90.99 335	84.87 267	92.96 248	96.29 182	60.69 392	98.80 144	80.18 322	97.11 269	95.71 305

CS-MVS		95.77 64	95.58 80	96.37 54	96.84 163	91.72 65	96.73 28	99.06 8	94.23 56	92.48 263	94.79 255	93.56 84	99.49 28	93.47 70	99.05 106	97.89 183

pmmvs6		96.80 16	97.36 10	95.15 100	99.12 8	87.82 132	96.68 29	97.86 95	96.10 33	98.14 28	99.28 5	97.94 3	98.21 216	91.38 138	99.69 14	99.42 20

mvsmamba		90.24 243	89.43 256	92.64 202	95.52 262	82.36 236	96.64 30	92.29 317	81.77 304	92.14 278	96.28 184	70.59 344	99.10 99	84.44 280	95.22 325	96.47 269

3Dnovator	92.54 3	94.80 106	94.90 106	94.47 131	95.47 264	87.06 145	96.63 31	97.28 148	91.82 116	94.34 198	97.41 94	90.60 164	98.65 173	92.47 107	98.11 215	97.70 204

PS-CasMVS		96.69 24	97.43 6	94.49 130	99.13 6	84.09 209	96.61 32	97.97 86	97.91 6	98.64 14	98.13 43	95.24 40	99.65 5	93.39 77	99.84 3	99.72 4

mvs_tets		96.83 12	96.71 22	97.17 31	98.83 24	92.51 52	96.58 33	97.61 117	87.57 217	98.80 8	98.90 11	96.50 9	99.59 14	96.15 13	99.47 41	99.40 22

PEN-MVS		96.69 24	97.39 9	94.61 120	99.16 4	84.50 199	96.54 34	98.05 73	98.06 5	98.64 14	98.25 40	95.01 53	99.65 5	92.95 94	99.83 5	99.68 6

MVSMamba_PlusPlus		94.82 105	95.89 64	91.62 240	97.82 104	78.88 295	96.52 35	97.60 119	97.14 14	94.23 199	98.48 32	87.01 214	99.71 3	95.43 25	98.80 144	96.28 278

DTE-MVSNet		96.74 21	97.43 6	94.67 117	99.13 6	84.68 198	96.51 36	97.94 92	98.14 4	98.67 13	98.32 37	95.04 50	99.69 4	93.27 82	99.82 7	99.62 12

XVS		96.49 33	96.18 46	97.44 20	98.56 41	93.99 30	96.50 37	97.95 89	94.58 50	94.38 196	96.49 164	94.56 69	99.39 52	93.57 63	99.05 106	98.93 68

X-MVStestdata		90.70 225	88.45 273	97.44 20	98.56 41	93.99 30	96.50 37	97.95 89	94.58 50	94.38 196	26.89 421	94.56 69	99.39 52	93.57 63	99.05 106	98.93 68

mmtdpeth		95.82 62	96.02 58	95.23 95	96.91 157	88.62 113	96.49 39	99.26 4	95.07 44	93.41 224	99.29 4	90.25 170	97.27 292	94.49 39	99.01 113	99.80 3

EC-MVSNet		95.44 76	95.62 78	94.89 106	96.93 156	87.69 134	96.48 40	99.14 7	93.93 63	92.77 254	94.52 266	93.95 81	99.49 28	93.62 62	99.22 89	97.51 217

mPP-MVS		96.46 35	96.05 55	97.69 6	98.62 35	94.65 17	96.45 41	97.74 108	92.59 87	95.47 145	96.68 156	94.50 71	99.42 36	93.10 88	99.26 82	98.99 56

QAPM		92.88 173	92.77 175	93.22 183	95.82 242	83.31 218	96.45 41	97.35 140	83.91 277	93.75 215	96.77 146	89.25 184	98.88 127	84.56 278	97.02 272	97.49 218

jajsoiax		96.59 31	96.42 33	97.12 33	98.76 30	92.49 53	96.44 43	97.42 132	86.96 227	98.71 11	98.72 19	95.36 34	99.56 18	95.92 14	99.45 45	99.32 27

Gipuma		95.31 87	95.80 72	93.81 158	97.99 95	90.91 74	96.42 44	97.95 89	96.69 19	91.78 284	98.85 14	91.77 132	95.49 353	91.72 126	99.08 102	95.02 329
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MSP-MVS		95.34 83	94.63 122	97.48 18	98.67 32	94.05 27	96.41 45	98.18 49	91.26 135	95.12 169	95.15 237	86.60 224	99.50 22	93.43 76	96.81 282	98.89 75
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
SR-MVS-dyc-post		96.84 11	96.60 28	97.56 14	98.07 84	95.27 10	96.37 46	98.12 59	95.66 39	97.00 69	97.03 130	94.85 60	99.42 36	93.49 67	98.84 135	98.00 166

RE-MVS-def			96.66 23		98.07 84	95.27 10	96.37 46	98.12 59	95.66 39	97.00 69	97.03 130	95.40 31		93.49 67	98.84 135	98.00 166

TSAR-MVS + MP.		94.96 99	94.75 112	95.57 80	98.86 22	88.69 110	96.37 46	96.81 182	85.23 257	94.75 186	97.12 123	91.85 129	99.40 49	93.45 72	98.33 193	98.62 115
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SPE-MVS-test		95.32 84	95.10 101	95.96 60	96.86 161	90.75 78	96.33 49	99.20 5	93.99 60	91.03 297	93.73 292	93.52 86	99.55 19	91.81 123	99.45 45	97.58 211

ACMH	88.36 12	96.59 31	97.43 6	94.07 144	98.56 41	85.33 192	96.33 49	98.30 33	94.66 49	98.72 9	98.30 38	97.51 5	98.00 236	94.87 34	99.59 27	98.86 78
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
region2R		96.41 40	96.09 51	97.38 26	98.62 35	93.81 39	96.32 51	97.96 87	92.26 96	95.28 159	96.57 162	95.02 52	99.41 42	93.63 61	99.11 101	98.94 66

testf1		96.77 18	96.49 30	97.60 10	99.01 14	96.70 4	96.31 52	98.33 28	94.96 45	97.30 56	97.93 57	96.05 16	97.90 243	89.32 190	99.23 86	98.19 149

APD_test2		96.77 18	96.49 30	97.60 10	99.01 14	96.70 4	96.31 52	98.33 28	94.96 45	97.30 56	97.93 57	96.05 16	97.90 243	89.32 190	99.23 86	98.19 149

APD-MVS_3200maxsize		96.82 13	96.65 24	97.32 29	97.95 96	93.82 37	96.31 52	98.25 37	95.51 41	96.99 71	97.05 129	95.63 23	99.39 52	93.31 79	98.88 130	98.75 91

CP-MVSNet		96.19 49	96.80 20	94.38 135	98.99 16	83.82 212	96.31 52	97.53 125	97.60 8	98.34 20	97.52 86	91.98 127	99.63 8	93.08 90	99.81 8	99.70 5

HFP-MVS		96.39 42	96.17 48	97.04 35	98.51 49	93.37 43	96.30 56	97.98 84	92.35 93	95.63 137	96.47 165	95.37 32	99.27 80	93.78 57	99.14 99	98.48 127

ACMMPR		96.46 35	96.14 49	97.41 24	98.60 38	93.82 37	96.30 56	97.96 87	92.35 93	95.57 140	96.61 160	94.93 58	99.41 42	93.78 57	99.15 98	99.00 54

3Dnovator+	92.74 2	95.86 61	95.77 73	96.13 56	96.81 166	90.79 77	96.30 56	97.82 100	96.13 32	94.74 187	97.23 112	91.33 141	99.16 90	93.25 83	98.30 196	98.46 128

MIMVSNet1		95.52 73	95.45 84	95.72 75	99.14 5	89.02 105	96.23 59	96.87 178	93.73 67	97.87 31	98.49 31	90.73 161	99.05 105	86.43 253	99.60 25	99.10 47

balanced_conf03		93.45 154	94.17 137	91.28 254	95.81 244	78.40 302	96.20 60	97.48 129	88.56 195	95.29 158	97.20 117	85.56 237	99.21 84	92.52 106	98.91 127	96.24 281

test2506		85.42 330	84.57 333	87.96 334	97.81 105	66.53 395	96.14 61	56.35 424	89.04 181	93.55 221	98.10 44	42.88 421	98.68 168	88.09 221	99.18 94	98.67 104

SR-MVS		96.70 23	96.42 33	97.54 15	98.05 86	94.69 15	96.13 62	98.07 69	95.17 43	96.82 79	96.73 153	95.09 49	99.43 35	92.99 93	98.71 155	98.50 124

mamv4		98.21 2	97.86 3	99.26 1	98.24 74	99.36 1	96.10 63	99.32 2	98.75 2	99.58 2	98.70 20	91.78 131	99.88 1	98.60 1	99.67 20	98.54 120

MP-MVS		96.14 50	95.68 76	97.51 17	98.81 27	94.06 25	96.10 63	97.78 106	92.73 83	93.48 222	96.72 154	94.23 76	99.42 36	91.99 117	99.29 75	99.05 51
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		96.42 39	96.20 45	97.07 34	98.80 29	92.79 50	96.08 65	98.16 56	91.74 121	95.34 154	96.36 178	95.68 21	99.44 32	94.41 42	99.28 80	98.97 62

FA-MVS(test-final)		91.81 203	91.85 201	91.68 238	94.95 277	79.99 269	96.00 66	93.44 296	87.80 210	94.02 208	97.29 108	77.60 304	98.45 196	88.04 223	97.49 254	96.61 261

GBi-Net		93.21 163	92.96 170	93.97 147	95.40 266	84.29 202	95.99 67	96.56 199	88.63 191	95.10 170	98.53 28	81.31 277	98.98 113	86.74 243	98.38 187	98.65 106

test1		93.21 163	92.96 170	93.97 147	95.40 266	84.29 202	95.99 67	96.56 199	88.63 191	95.10 170	98.53 28	81.31 277	98.98 113	86.74 243	98.38 187	98.65 106

FMVSNet1		94.84 103	95.13 99	93.97 147	97.60 122	84.29 202	95.99 67	96.56 199	92.38 90	97.03 68	98.53 28	90.12 173	98.98 113	88.78 209	99.16 97	98.65 106

RPSCF		95.58 72	94.89 107	97.62 9	97.58 124	96.30 8	95.97 70	97.53 125	92.42 89	93.41 224	97.78 67	91.21 146	97.77 261	91.06 141	97.06 270	98.80 85

SixPastTwentyTwo		94.91 100	95.21 96	93.98 146	98.52 48	83.19 223	95.93 71	94.84 264	94.86 48	98.49 16	98.74 18	81.45 275	99.60 10	94.69 36	99.39 56	99.15 39

ambc				92.98 187	96.88 159	83.01 228	95.92 72	96.38 209		96.41 94	97.48 92	88.26 191	97.80 256	89.96 178	98.93 125	98.12 156

FC-MVSNet-test		95.32 84	95.88 65	93.62 166	98.49 56	81.77 242	95.90 73	98.32 30	93.93 63	97.53 45	97.56 81	88.48 188	99.40 49	92.91 95	99.83 5	99.68 6

reproduce_model		97.35 5	97.24 12	97.70 5	98.44 58	95.08 12	95.88 74	98.50 18	96.62 22	98.27 21	97.93 57	94.57 68	99.50 22	95.57 20	99.35 59	98.52 123

MTAPA		96.65 26	96.38 37	97.47 19	98.95 18	94.05 27	95.88 74	97.62 115	94.46 54	96.29 101	96.94 136	93.56 84	99.37 60	94.29 45	99.42 50	98.99 56

CPTT-MVS		94.74 107	94.12 139	96.60 47	98.15 79	93.01 46	95.84 76	97.66 112	89.21 180	93.28 232	95.46 226	88.89 186	98.98 113	89.80 180	98.82 141	97.80 195

ab-mvs		92.40 190	92.62 182	91.74 234	97.02 150	81.65 244	95.84 76	95.50 245	86.95 228	92.95 249	97.56 81	90.70 162	97.50 278	79.63 330	97.43 258	96.06 289

nrg030		96.32 44	96.55 29	95.62 78	97.83 103	88.55 118	95.77 78	98.29 36	92.68 84	98.03 30	97.91 62	95.13 45	98.95 120	93.85 55	99.49 40	99.36 25

ECVR-MVS		90.12 247	90.16 241	90.00 297	97.81 105	72.68 366	95.76 79	78.54 414	89.04 181	95.36 153	98.10 44	70.51 345	98.64 174	87.10 239	99.18 94	98.67 104

SteuartSystems-ACMMP		96.40 41	96.30 40	96.71 44	98.63 34	91.96 59	95.70 80	98.01 81	93.34 77	96.64 87	96.57 162	94.99 54	99.36 61	93.48 69	99.34 63	98.82 82
Skip Steuart: Steuart Systems R&D Blog.
OpenMVS	89.45 8	92.27 196	92.13 194	92.68 201	94.53 295	84.10 208	95.70 80	97.03 164	82.44 298	91.14 296	96.42 169	88.47 189	98.38 201	85.95 258	97.47 256	95.55 314

GST-MVS		96.24 47	95.99 59	97.00 37	98.65 33	92.71 51	95.69 82	98.01 81	92.08 102	95.74 132	96.28 184	95.22 42	99.42 36	93.17 86	99.06 103	98.88 77

ACMH+	88.43 11	96.48 34	96.82 19	95.47 83	98.54 46	89.06 104	95.65 83	98.61 15	96.10 33	98.16 27	97.52 86	96.90 7	98.62 175	90.30 164	99.60 25	98.72 96

APD_test1		95.91 57	95.42 87	97.36 27	98.82 25	96.62 7	95.64 84	97.64 113	93.38 76	95.89 124	97.23 112	93.35 92	97.66 271	88.20 216	98.66 163	97.79 196

sasdasda		94.59 113	94.69 116	94.30 136	95.60 258	87.03 146	95.59 85	98.24 40	91.56 127	95.21 165	92.04 334	94.95 55	98.66 170	91.45 135	97.57 251	97.20 237

test1111		90.39 236	90.61 232	89.74 301	98.04 89	71.50 372	95.59 85	79.72 411	89.41 173	95.94 120	98.14 42	70.79 343	98.81 141	88.52 214	99.32 69	98.90 74

canonicalmvs		94.59 113	94.69 116	94.30 136	95.60 258	87.03 146	95.59 85	98.24 40	91.56 127	95.21 165	92.04 334	94.95 55	98.66 170	91.45 135	97.57 251	97.20 237

SF-MVS		95.88 60	95.88 65	95.87 70	98.12 80	89.65 90	95.58 88	98.56 17	91.84 113	96.36 96	96.68 156	94.37 75	99.32 71	92.41 108	99.05 106	98.64 111

reproduce-ours		97.28 7	97.19 14	97.57 12	98.37 63	94.84 13	95.57 89	98.40 24	96.36 29	98.18 25	97.78 67	95.47 28	99.50 22	95.26 30	99.33 65	98.36 133

our_new_method		97.28 7	97.19 14	97.57 12	98.37 63	94.84 13	95.57 89	98.40 24	96.36 29	98.18 25	97.78 67	95.47 28	99.50 22	95.26 30	99.33 65	98.36 133

PS-MVSNAJss		96.01 54	96.04 56	95.89 69	98.82 25	88.51 119	95.57 89	97.88 93	88.72 189	98.81 7	98.86 12	90.77 157	99.60 10	95.43 25	99.53 37	99.57 15

PMVS	87.21 14	94.97 98	95.33 91	93.91 152	98.97 17	97.16 3	95.54 92	95.85 230	96.47 25	93.40 227	97.46 93	95.31 37	95.47 354	86.18 257	98.78 147	89.11 399
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
VDDNet		94.03 138	94.27 134	93.31 180	98.87 21	82.36 236	95.51 93	91.78 329	97.19 13	96.32 98	98.60 25	84.24 246	98.75 152	87.09 240	98.83 140	98.81 84

pm-mvs1		95.43 77	95.94 60	93.93 151	98.38 61	85.08 195	95.46 94	97.12 159	91.84 113	97.28 58	98.46 33	95.30 38	97.71 268	90.17 171	99.42 50	98.99 56

RRT-MVS		92.28 194	93.01 169	90.07 293	94.06 306	73.01 362	95.36 95	97.88 93	92.24 98	95.16 167	97.52 86	78.51 298	99.29 74	90.55 154	95.83 308	97.92 179

Vis-MVSNet		95.50 74	95.48 83	95.56 81	98.11 81	89.40 97	95.35 96	98.22 44	92.36 92	94.11 201	98.07 46	92.02 125	99.44 32	93.38 78	97.67 246	97.85 189
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test0726					98.51 49	86.69 156	95.34 97	98.18 49	91.85 110	97.63 38	97.37 97	95.58 24

FIs		94.90 101	95.35 89	93.55 169	98.28 69	81.76 243	95.33 98	98.14 57	93.05 82	97.07 64	97.18 118	87.65 202	99.29 74	91.72 126	99.69 14	99.61 13

PGM-MVS		96.32 44	95.94 60	97.43 22	98.59 40	93.84 36	95.33 98	98.30 33	91.40 132	95.76 129	96.87 141	95.26 39	99.45 31	92.77 96	99.21 90	99.00 54

LPG-MVS_test		96.38 43	96.23 43	96.84 42	98.36 66	92.13 56	95.33 98	98.25 37	91.78 117	97.07 64	97.22 114	96.38 12	99.28 78	92.07 115	99.59 27	99.11 44

MonoMVSNet		88.46 286	89.28 257	85.98 362	90.52 379	70.07 381	95.31 101	94.81 267	88.38 198	93.47 223	96.13 194	73.21 332	95.07 363	82.61 294	89.12 398	92.81 379

AllTest		94.88 102	94.51 124	96.00 58	98.02 90	92.17 54	95.26 102	98.43 21	90.48 154	95.04 174	96.74 151	92.54 116	97.86 251	85.11 270	98.98 115	97.98 170

MGCFI-Net		94.44 120	94.67 120	93.75 160	95.56 260	85.47 189	95.25 103	98.24 40	91.53 129	95.04 174	92.21 329	94.94 57	98.54 186	91.56 133	97.66 247	97.24 235

SED-MVS		96.00 55	96.41 36	94.76 112	98.51 49	86.97 148	95.21 104	98.10 63	91.95 104	97.63 38	97.25 110	96.48 10	99.35 62	93.29 80	99.29 75	97.95 174

OPU-MVS				95.15 100	96.84 163	89.43 95	95.21 104				95.66 218	93.12 100	98.06 228	86.28 256	98.61 165	97.95 174

DVP-MVS		95.82 62	96.18 46	94.72 114	98.51 49	86.69 156	95.20 106	97.00 166	91.85 110	97.40 54	97.35 103	95.58 24	99.34 65	93.44 73	99.31 70	98.13 155
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				94.88 107	98.55 44	86.72 155	95.20 106	98.22 44					99.38 58	93.44 73	99.31 70	98.53 122

Anonymous20240529		95.50 74	95.83 69	94.50 128	97.33 138	85.93 178	95.19 108	96.77 186	96.64 21	97.61 41	98.05 47	93.23 96	98.79 145	88.60 213	99.04 111	98.78 87

SMA-MVS		95.77 64	95.54 81	96.47 53	98.27 70	91.19 70	95.09 109	97.79 105	86.48 230	97.42 52	97.51 90	94.47 74	99.29 74	93.55 65	99.29 75	98.93 68
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
NR-MVSNet		95.28 88	95.28 94	95.26 92	97.75 109	87.21 141	95.08 110	97.37 134	93.92 65	97.65 37	95.90 203	90.10 175	99.33 70	90.11 173	99.66 21	99.26 30

TransMVSNet (Re)		95.27 91	96.04 56	92.97 188	98.37 63	81.92 241	95.07 111	96.76 187	93.97 62	97.77 34	98.57 26	95.72 20	97.90 243	88.89 207	99.23 86	99.08 48

UGNet		93.08 166	92.50 185	94.79 111	93.87 311	87.99 128	95.07 111	94.26 280	90.64 150	87.33 362	97.67 74	86.89 219	98.49 190	88.10 220	98.71 155	97.91 180
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
tttt0517		89.81 257	88.90 267	92.55 210	97.00 151	79.73 277	95.03 113	83.65 394	89.88 165	95.30 156	94.79 255	53.64 403	99.39 52	91.99 117	98.79 146	98.54 120

LFMVS		91.33 216	91.16 219	91.82 231	96.27 208	79.36 284	95.01 114	85.61 381	96.04 36	94.82 183	97.06 128	72.03 339	98.46 195	84.96 273	98.70 157	97.65 208

CSCG		94.69 110	94.75 112	94.52 127	97.55 126	87.87 130	95.01 114	97.57 121	92.68 84	96.20 109	93.44 300	91.92 128	98.78 148	89.11 201	99.24 85	96.92 249

GG-mvs-BLEND				83.24 386	85.06 417	71.03 374	94.99 116	65.55 422		74.09 416	75.51 416	44.57 414	94.46 371	59.57 413	87.54 403	84.24 409

EU-MVSNet		87.39 308	86.71 313	89.44 305	93.40 318	76.11 334	94.93 117	90.00 343	57.17 416	95.71 135	97.37 97	64.77 373	97.68 270	92.67 101	94.37 345	94.52 345

KD-MVS_self_test		94.10 136	94.73 115	92.19 219	97.66 120	79.49 282	94.86 118	97.12 159	89.59 171	96.87 75	97.65 75	90.40 168	98.34 206	89.08 202	99.35 59	98.75 91

MTMP							94.82 119	54.62 425

PHI-MVS		94.34 126	93.80 146	95.95 61	95.65 254	91.67 66	94.82 119	97.86 95	87.86 209	93.04 244	94.16 277	91.58 136	98.78 148	90.27 166	98.96 122	97.41 223

gg-mvs-nofinetune		82.10 361	81.02 363	85.34 368	87.46 407	71.04 373	94.74 121	67.56 421	96.44 26	79.43 411	98.99 8	45.24 412	96.15 337	67.18 401	92.17 384	88.85 400

ACMM	88.83 9	96.30 46	96.07 54	96.97 38	98.39 60	92.95 48	94.74 121	98.03 78	90.82 145	97.15 61	96.85 142	96.25 14	99.00 112	93.10 88	99.33 65	98.95 65
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SD-MVS		95.19 92	95.73 74	93.55 169	96.62 177	88.88 109	94.67 123	98.05 73	91.26 135	97.25 60	96.40 171	95.42 30	94.36 374	92.72 100	99.19 92	97.40 226
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
API-MVS		91.52 212	91.61 205	91.26 255	94.16 301	86.26 170	94.66 124	94.82 265	91.17 138	92.13 279	91.08 348	90.03 178	97.06 307	79.09 337	97.35 262	90.45 397

v10		94.68 111	95.27 95	92.90 193	96.57 179	80.15 261	94.65 125	97.57 121	90.68 149	97.43 50	98.00 52	88.18 192	99.15 91	94.84 35	99.55 35	99.41 21

v8		94.65 112	95.29 93	92.74 198	96.65 173	79.77 276	94.59 126	97.17 154	91.86 109	97.47 49	97.93 57	88.16 193	99.08 100	94.32 43	99.47 41	99.38 23

APD-MVS		95.00 97	94.69 116	95.93 64	97.38 134	90.88 75	94.59 126	97.81 101	89.22 179	95.46 147	96.17 193	93.42 90	99.34 65	89.30 192	98.87 133	97.56 214
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
VPA-MVSNet		95.14 93	95.67 77	93.58 168	97.76 108	83.15 224	94.58 128	97.58 120	93.39 75	97.05 67	98.04 49	93.25 95	98.51 189	89.75 183	99.59 27	99.08 48

ACMMP_NAP		96.21 48	96.12 50	96.49 52	98.90 19	91.42 67	94.57 129	98.03 78	90.42 157	96.37 95	97.35 103	95.68 21	99.25 81	94.44 41	99.34 63	98.80 85

HQP_MVS		94.26 129	93.93 142	95.23 95	97.71 114	88.12 125	94.56 130	97.81 101	91.74 121	93.31 229	95.59 220	86.93 217	98.95 120	89.26 196	98.51 177	98.60 116

plane_prior2							94.56 130		91.74 121

tfpnnormal		94.27 128	94.87 108	92.48 212	97.71 114	80.88 256	94.55 132	95.41 249	93.70 68	96.67 86	97.72 72	91.40 140	98.18 220	87.45 233	99.18 94	98.36 133

XVG-ACMP-BASELINE		95.68 68	95.34 90	96.69 45	98.40 59	93.04 45	94.54 133	98.05 73	90.45 156	96.31 99	96.76 148	92.91 107	98.72 157	91.19 139	99.42 50	98.32 138

DP-MVS		95.62 69	95.84 68	94.97 104	97.16 146	88.62 113	94.54 133	97.64 113	96.94 17	96.58 90	97.32 107	93.07 103	98.72 157	90.45 156	98.84 135	97.57 212

MIMVSNet		87.13 316	86.54 317	88.89 316	96.05 227	76.11 334	94.39 135	88.51 350	81.37 308	88.27 348	96.75 150	72.38 336	95.52 351	65.71 404	95.47 316	95.03 328

K. test v3		93.37 156	93.27 166	93.66 164	98.05 86	82.62 232	94.35 136	86.62 369	96.05 35	97.51 46	98.85 14	76.59 320	99.65 5	93.21 84	98.20 208	98.73 95

Vis-MVSNet (Re-imp)		90.42 233	90.16 241	91.20 259	97.66 120	77.32 318	94.33 137	87.66 361	91.20 137	92.99 245	95.13 239	75.40 325	98.28 209	77.86 342	99.19 92	97.99 169

ANet_high		94.83 104	96.28 41	90.47 281	96.65 173	73.16 360	94.33 137	98.74 14	96.39 28	98.09 29	98.93 10	93.37 91	98.70 164	90.38 159	99.68 17	99.53 16

MM		94.41 122	94.14 138	95.22 97	95.84 240	87.21 141	94.31 139	90.92 337	94.48 53	92.80 252	97.52 86	85.27 238	99.49 28	96.58 8	99.57 33	98.97 62

test_fmvsmconf0.01_n		95.90 58	96.09 51	95.31 91	97.30 139	89.21 100	94.24 140	98.76 13	86.25 234	97.56 42	98.66 21	95.73 19	98.44 197	97.35 3	98.99 114	98.27 143

ACMP	88.15 13	95.71 67	95.43 86	96.54 49	98.17 78	91.73 64	94.24 140	98.08 66	89.46 172	96.61 89	96.47 165	95.85 18	99.12 96	90.45 156	99.56 34	98.77 90
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MAR-MVS		90.32 241	88.87 268	94.66 119	94.82 281	91.85 61	94.22 142	94.75 269	80.91 312	87.52 360	88.07 382	86.63 223	97.87 250	76.67 353	96.21 299	94.25 351
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
FMVSNet2		92.78 178	92.73 179	92.95 190	95.40 266	81.98 240	94.18 143	95.53 244	88.63 191	96.05 116	97.37 97	81.31 277	98.81 141	87.38 236	98.67 161	98.06 158

fmvsm_s_conf0.1_n_a		94.26 129	94.37 128	93.95 150	97.36 136	85.72 184	94.15 144	95.44 246	83.25 284	95.51 142	98.05 47	92.54 116	97.19 298	95.55 21	97.46 257	98.94 66

Anonymous20240521		92.86 176	93.57 157	90.74 275	96.57 179	75.50 341	94.15 144	95.60 236	89.38 174	95.90 123	97.90 64	80.39 284	97.96 240	92.60 104	99.68 17	98.75 91

GeoE		94.55 116	94.68 119	94.15 140	97.23 141	85.11 194	94.14 146	97.34 141	88.71 190	95.26 160	95.50 225	94.65 65	99.12 96	90.94 145	98.40 183	98.23 145

9.14			94.81 109		97.49 129		94.11 147	98.37 26	87.56 218	95.38 150	96.03 199	94.66 64	99.08 100	90.70 150	98.97 120

BP-MVS1		91.77 204	91.10 220	93.75 160	96.42 192	83.40 217	94.10 148	91.89 327	91.27 134	93.36 228	94.85 250	64.43 374	99.29 74	94.88 33	98.74 152	98.56 119

HPM-MVS++		95.02 96	94.39 126	96.91 41	97.88 100	93.58 41	94.09 149	96.99 168	91.05 140	92.40 268	95.22 236	91.03 153	99.25 81	92.11 112	98.69 158	97.90 181

HY-MVS	82.50 18	86.81 322	85.93 324	89.47 304	93.63 315	77.93 308	94.02 150	91.58 332	75.68 355	83.64 388	93.64 293	77.40 307	97.42 284	71.70 385	92.07 385	93.05 376

Effi-MVS+-dtu		93.90 144	92.60 183	97.77 4	94.74 287	96.67 6	94.00 151	95.41 249	89.94 163	91.93 283	92.13 332	90.12 173	98.97 117	87.68 230	97.48 255	97.67 207

Effi-MVS+		92.79 177	92.74 177	92.94 191	95.10 274	83.30 219	94.00 151	97.53 125	91.36 133	89.35 329	90.65 357	94.01 80	98.66 170	87.40 235	95.30 322	96.88 253

VDD-MVS		94.37 123	94.37 128	94.40 134	97.49 129	86.07 175	93.97 153	93.28 298	94.49 52	96.24 105	97.78 67	87.99 198	98.79 145	88.92 205	99.14 99	98.34 137

h-mvs33		92.89 172	91.99 197	95.58 79	96.97 152	90.55 80	93.94 154	94.01 286	89.23 177	93.95 210	96.19 190	76.88 316	99.14 93	91.02 142	95.71 310	97.04 245

EPNet		89.80 258	88.25 281	94.45 132	83.91 419	86.18 172	93.87 155	87.07 367	91.16 139	80.64 408	94.72 257	78.83 292	98.89 126	85.17 265	98.89 128	98.28 142
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvs3		92.42 189	92.40 188	92.46 214	93.80 314	87.28 139	93.86 156	97.05 163	76.86 350	96.25 104	98.66 21	82.87 259	91.26 393	95.44 24	96.83 281	98.82 82

DeepC-MVS	91.39 4	95.43 77	95.33 91	95.71 76	97.67 119	90.17 84	93.86 156	98.02 80	87.35 219	96.22 107	97.99 54	94.48 73	99.05 105	92.73 99	99.68 17	97.93 177
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LCM-MVSNet-Re		94.20 133	94.58 123	93.04 185	95.91 237	83.13 225	93.79 158	99.19 6	92.00 103	98.84 6	98.04 49	93.64 83	99.02 110	81.28 311	98.54 173	96.96 248

TranMVSNet+NR-MVSNet		96.07 53	96.26 42	95.50 82	98.26 71	87.69 134	93.75 159	97.86 95	95.96 38	97.48 48	97.14 121	95.33 36	99.44 32	90.79 147	99.76 10	99.38 23

fmvsm_s_conf0.1_n		94.19 135	94.41 125	93.52 174	97.22 143	84.37 200	93.73 160	95.26 253	84.45 272	95.76 129	98.00 52	91.85 129	97.21 295	95.62 17	97.82 238	98.98 60

PAPM_NR		91.03 220	90.81 227	91.68 238	96.73 168	81.10 253	93.72 161	96.35 210	88.19 202	88.77 339	92.12 333	85.09 241	97.25 293	82.40 299	93.90 357	96.68 260

baseline		94.26 129	94.80 110	92.64 202	96.08 225	80.99 254	93.69 162	98.04 77	90.80 146	94.89 181	96.32 180	93.19 97	98.48 194	91.68 128	98.51 177	98.43 131

dcpmvs_2		93.96 141	95.01 104	90.82 273	97.60 122	74.04 355	93.68 163	98.85 10	89.80 167	97.82 32	97.01 133	91.14 151	99.21 84	90.56 153	98.59 168	99.19 36

GDP-MVS		91.56 210	90.83 226	93.77 159	96.34 200	83.65 214	93.66 164	98.12 59	87.32 221	92.98 247	94.71 258	63.58 380	99.30 73	92.61 103	98.14 212	98.35 136

fmvsm_s_conf0.5_n_a		94.02 139	94.08 141	93.84 156	96.72 169	85.73 183	93.65 165	95.23 254	83.30 282	95.13 168	97.56 81	92.22 121	97.17 299	95.51 22	97.41 259	98.64 111

F-COLMAP		92.28 194	91.06 221	95.95 61	97.52 127	91.90 60	93.53 166	97.18 153	83.98 276	88.70 341	94.04 280	88.41 190	98.55 185	80.17 323	95.99 303	97.39 227

test_fmvsmconf0.1_n		95.61 70	95.72 75	95.26 92	96.85 162	89.20 101	93.51 167	98.60 16	85.68 248	97.42 52	98.30 38	95.34 35	98.39 198	96.85 4	98.98 115	98.19 149

FMVSNet5		87.82 297	86.56 316	91.62 240	92.31 341	79.81 275	93.49 168	94.81 267	83.26 283	91.36 290	96.93 137	52.77 405	97.49 280	76.07 359	98.03 223	97.55 215

DPE-MVS		95.89 59	95.88 65	95.92 66	97.93 97	89.83 88	93.46 169	98.30 33	92.37 91	97.75 35	96.95 135	95.14 44	99.51 21	91.74 125	99.28 80	98.41 132
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
alignmvs		93.26 160	92.85 174	94.50 128	95.70 250	87.45 136	93.45 170	95.76 231	91.58 126	95.25 162	92.42 327	81.96 272	98.72 157	91.61 129	97.87 236	97.33 231

test_fmvsmvis_n_1920		95.08 95	95.40 88	94.13 142	96.66 172	87.75 133	93.44 171	98.49 19	85.57 252	98.27 21	97.11 124	94.11 79	97.75 264	96.26 11	98.72 153	96.89 251

114514_t		90.51 230	89.80 250	92.63 205	98.00 92	82.24 238	93.40 172	97.29 146	65.84 407	89.40 328	94.80 254	86.99 215	98.75 152	83.88 284	98.61 165	96.89 251

fmvsm_s_conf0.5_n		94.00 140	94.20 136	93.42 178	96.69 170	84.37 200	93.38 173	95.13 256	84.50 271	95.40 149	97.55 85	91.77 132	97.20 296	95.59 18	97.79 239	98.69 103

DeepC-MVS_fast	89.96 7	93.73 147	93.44 161	94.60 123	96.14 220	87.90 129	93.36 174	97.14 156	85.53 253	93.90 213	95.45 227	91.30 143	98.59 180	89.51 186	98.62 164	97.31 232
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS-pluss		96.08 52	95.92 63	96.57 48	99.06 10	91.21 69	93.25 175	98.32 30	87.89 208	96.86 76	97.38 96	95.55 26	99.39 52	95.47 23	99.47 41	99.11 44
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_0402		95.73 66	96.22 44	94.26 138	98.19 77	85.77 182	93.24 176	97.24 150	96.88 18	97.69 36	97.77 71	94.12 78	99.13 95	91.54 134	99.29 75	97.88 184

test_fmvsmconf_n		95.43 77	95.50 82	95.22 97	96.48 189	89.19 102	93.23 177	98.36 27	85.61 251	96.92 74	98.02 51	95.23 41	98.38 201	96.69 7	98.95 124	98.09 157

test_fmvsm_n_1920		94.72 108	94.74 114	94.67 117	96.30 206	88.62 113	93.19 178	98.07 69	85.63 250	97.08 63	97.35 103	90.86 154	97.66 271	95.70 16	98.48 180	97.74 202

sd_testset		93.94 142	94.39 126	92.61 207	97.93 97	83.24 220	93.17 179	95.04 258	93.65 72	95.51 142	98.63 23	94.49 72	95.89 346	81.72 306	99.35 59	98.70 100

MSLP-MVS++		93.25 162	93.88 143	91.37 248	96.34 200	82.81 231	93.11 180	97.74 108	89.37 175	94.08 203	95.29 235	90.40 168	96.35 334	90.35 161	98.25 201	94.96 330

baseline1		87.62 302	87.31 297	88.54 323	94.71 290	74.27 352	93.10 181	88.20 354	86.20 236	92.18 277	93.04 309	73.21 332	95.52 351	79.32 334	85.82 406	95.83 300

plane_prior						88.12 125	93.01 182		88.98 183						98.06 220

thres100view900		87.35 309	86.89 309	88.72 319	96.14 220	73.09 361	93.00 183	85.31 384	92.13 101	93.26 234	90.96 350	63.42 381	98.28 209	71.27 388	96.54 291	94.79 338

Patchmtry		90.11 248	89.92 247	90.66 277	90.35 383	77.00 322	92.96 184	92.81 305	90.25 160	94.74 187	96.93 137	67.11 356	97.52 277	85.17 265	98.98 115	97.46 219

LF4IMVS		92.72 180	92.02 196	94.84 109	95.65 254	91.99 58	92.92 185	96.60 195	85.08 263	92.44 266	93.62 295	86.80 220	96.35 334	86.81 242	98.25 201	96.18 284

UniMVSNet (Re)		95.32 84	95.15 98	95.80 72	97.79 107	88.91 107	92.91 186	98.07 69	93.46 74	96.31 99	95.97 202	90.14 172	99.34 65	92.11 112	99.64 23	99.16 38

TAPA-MVS	88.58 10	92.49 187	91.75 204	94.73 113	96.50 186	89.69 89	92.91 186	97.68 111	78.02 341	92.79 253	94.10 278	90.85 155	97.96 240	84.76 276	98.16 210	96.54 262
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVS_0304		92.88 173	92.27 189	94.69 116	92.35 340	86.03 176	92.88 188	89.68 344	90.53 153	91.52 287	96.43 168	82.52 266	99.32 71	95.01 32	99.54 36	98.71 99

thisisatest0530		88.69 283	87.52 295	92.20 218	96.33 202	79.36 284	92.81 189	84.01 393	86.44 231	93.67 218	92.68 320	53.62 404	99.25 81	89.65 185	98.45 181	98.00 166

EIA-MVS		92.35 192	92.03 195	93.30 181	95.81 244	83.97 210	92.80 190	98.17 53	87.71 213	89.79 322	87.56 384	91.17 150	99.18 89	87.97 225	97.27 263	96.77 257

thres600view7		87.66 300	87.10 306	89.36 308	96.05 227	73.17 359	92.72 191	85.31 384	91.89 108	93.29 231	90.97 349	63.42 381	98.39 198	73.23 376	96.99 277	96.51 264

wuyk23d		87.83 296	90.79 228	78.96 396	90.46 382	88.63 112	92.72 191	90.67 340	91.65 125	98.68 12	97.64 76	96.06 15	77.53 418	59.84 412	99.41 54	70.73 416

test_fmvs2		90.62 229	90.40 238	91.29 253	91.93 356	85.46 190	92.70 193	96.48 205	74.44 365	94.91 180	97.59 79	75.52 324	90.57 396	93.44 73	96.56 290	97.84 190

V42		93.43 155	93.58 156	92.97 188	95.34 270	81.22 251	92.67 194	96.49 204	87.25 222	96.20 109	96.37 177	87.32 208	98.85 133	92.39 109	98.21 206	98.85 81

casdiffmvs_mvg		95.10 94	95.62 78	93.53 172	96.25 211	83.23 221	92.66 195	98.19 47	93.06 81	97.49 47	97.15 120	94.78 61	98.71 163	92.27 110	98.72 153	98.65 106
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
OPM-MVS		95.61 70	95.45 84	96.08 57	98.49 56	91.00 72	92.65 196	97.33 142	90.05 162	96.77 82	96.85 142	95.04 50	98.56 183	92.77 96	99.06 103	98.70 100
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test_vis1_n		89.01 273	89.01 263	89.03 313	92.57 335	82.46 235	92.62 197	96.06 222	73.02 375	90.40 308	95.77 214	74.86 326	89.68 402	90.78 148	94.98 330	94.95 331

DU-MVS		95.28 88	95.12 100	95.75 74	97.75 109	88.59 116	92.58 198	97.81 101	93.99 60	96.80 80	95.90 203	90.10 175	99.41 42	91.60 130	99.58 31	99.26 30

FMVSNet3		90.78 223	90.32 240	92.16 223	93.03 326	79.92 271	92.54 199	94.95 261	86.17 238	95.10 170	96.01 200	69.97 347	98.75 152	86.74 243	98.38 187	97.82 193

hse-mvs2		92.24 197	91.20 216	95.38 85	96.16 217	90.65 79	92.52 200	92.01 326	89.23 177	93.95 210	92.99 311	76.88 316	98.69 166	91.02 142	96.03 301	96.81 255

MVS_Test		92.57 186	93.29 163	90.40 284	93.53 317	75.85 337	92.52 200	96.96 169	88.73 188	92.35 271	96.70 155	90.77 157	98.37 205	92.53 105	95.49 315	96.99 247

CR-MVSNet		87.89 294	87.12 305	90.22 289	91.01 372	78.93 291	92.52 200	92.81 305	73.08 374	89.10 330	96.93 137	67.11 356	97.64 273	88.80 208	92.70 378	94.08 352

RPMNet		90.31 242	90.14 244	90.81 274	91.01 372	78.93 291	92.52 200	98.12 59	91.91 107	89.10 330	96.89 140	68.84 349	99.41 42	90.17 171	92.70 378	94.08 352

fmvsm_l_conf0.5_n		93.79 145	93.81 144	93.73 162	96.16 217	86.26 170	92.46 204	96.72 189	81.69 306	95.77 128	97.11 124	90.83 156	97.82 254	95.58 19	97.99 227	97.11 240

XVG-OURS-SEG-HR		95.38 81	95.00 105	96.51 50	98.10 82	94.07 24	92.46 204	98.13 58	90.69 148	93.75 215	96.25 188	98.03 2	97.02 308	92.08 114	95.55 313	98.45 129

EI-MVSNet-Vis-set		94.36 124	94.28 132	94.61 120	92.55 336	85.98 177	92.44 206	94.69 271	93.70 68	96.12 114	95.81 209	91.24 144	98.86 131	93.76 60	98.22 205	98.98 60

Anonymous202405211		92.58 184	92.50 185	92.83 196	96.55 181	83.22 222	92.43 207	91.64 331	94.10 59	95.59 139	96.64 158	81.88 274	97.50 278	85.12 269	98.52 175	97.77 198

AUN-MVS		90.05 252	88.30 277	95.32 90	96.09 224	90.52 81	92.42 208	92.05 325	82.08 302	88.45 345	92.86 313	65.76 366	98.69 166	88.91 206	96.07 300	96.75 259

EI-MVSNet-UG-set		94.35 125	94.27 134	94.59 124	92.46 339	85.87 180	92.42 208	94.69 271	93.67 71	96.13 113	95.84 207	91.20 147	98.86 131	93.78 57	98.23 203	99.03 52

NCCC		94.08 137	93.54 159	95.70 77	96.49 187	89.90 87	92.39 210	96.91 175	90.64 150	92.33 274	94.60 263	90.58 165	98.96 118	90.21 170	97.70 244	98.23 145

casdiffmvs		94.32 127	94.80 110	92.85 195	96.05 227	81.44 248	92.35 211	98.05 73	91.53 129	95.75 131	96.80 145	93.35 92	98.49 190	91.01 144	98.32 195	98.64 111
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ETV-MVS		92.99 169	92.74 177	93.72 163	95.86 239	86.30 169	92.33 212	97.84 98	91.70 124	92.81 251	86.17 394	92.22 121	99.19 88	88.03 224	97.73 241	95.66 309

fmvsm_l_conf0.5_n_a		93.59 150	93.63 153	93.49 176	96.10 223	85.66 186	92.32 213	96.57 198	81.32 309	95.63 137	97.14 121	90.19 171	97.73 267	95.37 28	98.03 223	97.07 241

EI-MVSNet		92.99 169	93.26 167	92.19 219	92.12 349	79.21 289	92.32 213	94.67 273	91.77 119	95.24 163	95.85 205	87.14 212	98.49 190	91.99 117	98.26 199	98.86 78

CVMVSNet		85.16 332	84.72 330	86.48 355	92.12 349	70.19 377	92.32 213	88.17 355	56.15 417	90.64 304	95.85 205	67.97 354	96.69 322	88.78 209	90.52 394	92.56 382

test_fmvs1_n		88.73 282	88.38 275	89.76 300	92.06 351	82.53 233	92.30 216	96.59 197	71.14 385	92.58 260	95.41 232	68.55 350	89.57 404	91.12 140	95.66 311	97.18 239

OMC-MVS		94.22 132	93.69 151	95.81 71	97.25 140	91.27 68	92.27 217	97.40 133	87.10 226	94.56 191	95.42 229	93.74 82	98.11 225	86.62 247	98.85 134	98.06 158

PM-MVS		93.33 157	92.67 181	95.33 88	96.58 178	94.06 25	92.26 218	92.18 319	85.92 242	96.22 107	96.61 160	85.64 235	95.99 344	90.35 161	98.23 203	95.93 295

UniMVSNet_NR-MVSNet		95.35 82	95.21 96	95.76 73	97.69 117	88.59 116	92.26 218	97.84 98	94.91 47	96.80 80	95.78 213	90.42 166	99.41 42	91.60 130	99.58 31	99.29 29

AdaColmap		91.63 208	91.36 213	92.47 213	95.56 260	86.36 167	92.24 220	96.27 212	88.88 187	89.90 319	92.69 319	91.65 135	98.32 207	77.38 349	97.64 248	92.72 381

PVSNet_Blended_VisFu		91.63 208	91.20 216	92.94 191	97.73 112	83.95 211	92.14 221	97.46 130	78.85 337	92.35 271	94.98 245	84.16 247	99.08 100	86.36 254	96.77 284	95.79 302

Baseline_NR-MVSNet		94.47 119	95.09 102	92.60 208	98.50 55	80.82 257	92.08 222	96.68 191	93.82 66	96.29 101	98.56 27	90.10 175	97.75 264	90.10 175	99.66 21	99.24 32

Fast-Effi-MVS+-dtu		92.77 179	92.16 191	94.58 126	94.66 292	88.25 123	92.05 223	96.65 193	89.62 170	90.08 314	91.23 345	92.56 115	98.60 178	86.30 255	96.27 298	96.90 250

save fliter					97.46 132	88.05 127	92.04 224	97.08 161	87.63 216

PatchT		87.51 305	88.17 286	85.55 366	90.64 376	66.91 392	92.02 225	86.09 373	92.20 99	89.05 332	97.16 119	64.15 376	96.37 333	89.21 199	92.98 376	93.37 371

EG-PatchMatch MVS		94.54 117	94.67 120	94.14 141	97.87 102	86.50 160	92.00 226	96.74 188	88.16 204	96.93 73	97.61 78	93.04 104	97.90 243	91.60 130	98.12 214	98.03 164

v144192		93.20 165	93.54 159	92.16 223	96.05 227	78.26 305	91.95 227	97.14 156	84.98 265	95.96 118	96.11 195	87.08 213	99.04 108	93.79 56	98.84 135	99.17 37

VNet		92.67 182	92.96 170	91.79 232	96.27 208	80.15 261	91.95 227	94.98 260	92.19 100	94.52 193	96.07 197	87.43 206	97.39 287	84.83 274	98.38 187	97.83 191

1314		86.46 324	86.33 321	86.87 351	91.65 363	74.54 347	91.94 229	94.10 282	74.28 366	84.78 379	87.33 388	83.03 257	95.00 364	78.72 338	91.16 391	91.06 394

MVS		84.98 334	84.30 335	87.01 346	91.03 371	77.69 314	91.94 229	94.16 281	59.36 415	84.23 384	87.50 386	85.66 233	96.80 319	71.79 383	93.05 375	86.54 407

SDMVSNet		94.43 121	95.02 103	92.69 200	97.93 97	82.88 230	91.92 231	95.99 227	93.65 72	95.51 142	98.63 23	94.60 67	96.48 327	87.57 231	99.35 59	98.70 100

tfpn200view9		87.05 318	86.52 318	88.67 320	95.77 246	72.94 363	91.89 232	86.00 374	90.84 143	92.61 258	89.80 361	63.93 377	98.28 209	71.27 388	96.54 291	94.79 338

thres400		87.20 313	86.52 318	89.24 312	95.77 246	72.94 363	91.89 232	86.00 374	90.84 143	92.61 258	89.80 361	63.93 377	98.28 209	71.27 388	96.54 291	96.51 264

v1921920		93.26 160	93.61 155	92.19 219	96.04 231	78.31 304	91.88 234	97.24 150	85.17 259	96.19 112	96.19 190	86.76 221	99.05 105	94.18 47	98.84 135	99.22 33

XXY-MVS		92.58 184	93.16 168	90.84 272	97.75 109	79.84 272	91.87 235	96.22 217	85.94 241	95.53 141	97.68 73	92.69 113	94.48 370	83.21 288	97.51 253	98.21 147

IterMVS-LS		93.78 146	94.28 132	92.27 216	96.27 208	79.21 289	91.87 235	96.78 184	91.77 119	96.57 91	97.07 127	87.15 211	98.74 155	91.99 117	99.03 112	98.86 78
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1144		93.50 151	93.81 144	92.57 209	96.28 207	79.61 279	91.86 237	96.96 169	86.95 228	95.91 122	96.32 180	87.65 202	98.96 118	93.51 66	98.88 130	99.13 41

v1192		93.49 152	93.78 147	92.62 206	96.16 217	79.62 278	91.83 238	97.22 152	86.07 239	96.10 115	96.38 176	87.22 209	99.02 110	94.14 48	98.88 130	99.22 33

v1240		93.29 158	93.71 150	92.06 226	96.01 232	77.89 310	91.81 239	97.37 134	85.12 261	96.69 85	96.40 171	86.67 222	99.07 104	94.51 38	98.76 149	99.22 33

CNVR-MVS		94.58 115	94.29 131	95.46 84	96.94 154	89.35 99	91.81 239	96.80 183	89.66 169	93.90 213	95.44 228	92.80 111	98.72 157	92.74 98	98.52 175	98.32 138

v2v482		93.29 158	93.63 153	92.29 215	96.35 199	78.82 297	91.77 241	96.28 211	88.45 196	95.70 136	96.26 187	86.02 230	98.90 124	93.02 91	98.81 143	99.14 40

EPNet_dtu		85.63 328	84.37 334	89.40 307	86.30 412	74.33 351	91.64 242	88.26 352	84.84 268	72.96 417	89.85 359	71.27 342	97.69 269	76.60 354	97.62 249	96.18 284
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PLC	85.34 15	90.40 234	88.92 265	94.85 108	96.53 185	90.02 85	91.58 243	96.48 205	80.16 318	86.14 368	92.18 330	85.73 232	98.25 214	76.87 352	94.61 341	96.30 276
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VPNet		93.08 166	93.76 148	91.03 263	98.60 38	75.83 339	91.51 244	95.62 235	91.84 113	95.74 132	97.10 126	89.31 183	98.32 207	85.07 272	99.06 103	98.93 68

ttmdpeth		86.91 321	86.57 315	87.91 337	89.68 390	74.24 353	91.49 245	87.09 365	79.84 319	89.46 327	97.86 65	65.42 368	91.04 394	81.57 308	96.74 287	98.44 130

XVG-OURS		94.72 108	94.12 139	96.50 51	98.00 92	94.23 22	91.48 246	98.17 53	90.72 147	95.30 156	96.47 165	87.94 199	96.98 309	91.41 137	97.61 250	98.30 141

HQP-NCC					96.36 196		91.37 247		87.16 223	88.81 335

ACMP_Plane					96.36 196		91.37 247		87.16 223	88.81 335

HQP-MVS		92.09 199	91.49 210	93.88 153	96.36 196	84.89 196	91.37 247	97.31 143	87.16 223	88.81 335	93.40 301	84.76 243	98.60 178	86.55 250	97.73 241	98.14 154

MCST-MVS		92.91 171	92.51 184	94.10 143	97.52 127	85.72 184	91.36 250	97.13 158	80.33 317	92.91 250	94.24 273	91.23 145	98.72 157	89.99 177	97.93 232	97.86 187

v148		92.87 175	93.29 163	91.62 240	96.25 211	77.72 313	91.28 251	95.05 257	89.69 168	95.93 121	96.04 198	87.34 207	98.38 201	90.05 176	97.99 227	98.78 87

tpmvs		84.22 341	83.97 339	84.94 372	87.09 409	65.18 402	91.21 252	88.35 351	82.87 292	85.21 372	90.96 350	65.24 371	96.75 320	79.60 333	85.25 407	92.90 378

reproduce_monomvs		87.13 316	86.90 308	87.84 339	90.92 374	68.15 387	91.19 253	93.75 289	85.84 243	94.21 200	95.83 208	42.99 418	97.10 303	89.46 188	97.88 235	98.26 144

CANet		92.38 191	91.99 197	93.52 174	93.82 313	83.46 216	91.14 254	97.00 166	89.81 166	86.47 366	94.04 280	87.90 200	99.21 84	89.50 187	98.27 198	97.90 181

CNLPA		91.72 206	91.20 216	93.26 182	96.17 216	91.02 71	91.14 254	95.55 243	90.16 161	90.87 298	93.56 298	86.31 226	94.40 373	79.92 329	97.12 268	94.37 348

DP-MVS Recon		92.31 193	91.88 200	93.60 167	97.18 145	86.87 151	91.10 256	97.37 134	84.92 266	92.08 280	94.08 279	88.59 187	98.20 217	83.50 285	98.14 212	95.73 304

OpenMVS_ROB	85.12 16	89.52 261	89.05 261	90.92 268	94.58 294	81.21 252	91.10 256	93.41 297	77.03 349	93.41 224	93.99 284	83.23 254	97.80 256	79.93 327	94.80 336	93.74 363

MVStest1		84.79 336	84.06 338	86.98 347	77.73 424	74.76 343	91.08 258	85.63 379	77.70 342	96.86 76	97.97 55	41.05 423	88.24 408	92.22 111	96.28 297	97.94 176

TSAR-MVS + GP.		93.07 168	92.41 187	95.06 102	95.82 242	90.87 76	90.97 259	92.61 313	88.04 205	94.61 190	93.79 291	88.08 194	97.81 255	89.41 189	98.39 186	96.50 267

MVP-Stereo		90.07 251	88.92 265	93.54 171	96.31 204	86.49 161	90.93 260	95.59 240	79.80 320	91.48 288	95.59 220	80.79 281	97.39 287	78.57 340	91.19 390	96.76 258
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVSTER		89.32 265	88.75 269	91.03 263	90.10 386	76.62 329	90.85 261	94.67 273	82.27 299	95.24 163	95.79 210	61.09 390	98.49 190	90.49 155	98.26 199	97.97 173

pmmvs-eth3d		91.54 211	90.73 230	93.99 145	95.76 248	87.86 131	90.83 262	93.98 287	78.23 340	94.02 208	96.22 189	82.62 265	96.83 318	86.57 248	98.33 193	97.29 233

CANet_DTU		89.85 256	89.17 259	91.87 229	92.20 346	80.02 268	90.79 263	95.87 229	86.02 240	82.53 398	91.77 338	80.01 285	98.57 182	85.66 262	97.70 244	97.01 246

SSC-MVS		90.16 245	92.96 170	81.78 390	97.88 100	48.48 422	90.75 264	87.69 360	96.02 37	96.70 84	97.63 77	85.60 236	97.80 256	85.73 261	98.60 167	99.06 50

test_prior4						89.91 86	90.74 265

TinyColmap		92.00 201	92.76 176	89.71 302	95.62 257	77.02 321	90.72 266	96.17 220	87.70 214	95.26 160	96.29 182	92.54 116	96.45 329	81.77 304	98.77 148	95.66 309

CDPH-MVS		92.67 182	91.83 202	95.18 99	96.94 154	88.46 121	90.70 267	97.07 162	77.38 344	92.34 273	95.08 242	92.67 114	98.88 127	85.74 260	98.57 170	98.20 148

test_vis1_n_1920		89.45 262	89.85 249	88.28 329	93.59 316	76.71 328	90.67 268	97.78 106	79.67 324	90.30 311	96.11 195	76.62 319	92.17 389	90.31 163	93.57 362	95.96 293

DSMNet-mixed		82.21 358	81.56 357	84.16 380	89.57 393	70.00 382	90.65 269	77.66 416	54.99 418	83.30 392	97.57 80	77.89 303	90.50 398	66.86 402	95.54 314	91.97 386

TEST9					96.45 190	89.46 93	90.60 270	96.92 173	79.09 333	90.49 305	94.39 269	91.31 142	98.88 127

train_agg		92.71 181	91.83 202	95.35 86	96.45 190	89.46 93	90.60 270	96.92 173	79.37 328	90.49 305	94.39 269	91.20 147	98.88 127	88.66 212	98.43 182	97.72 203

PatchmatchNet		85.22 331	84.64 331	86.98 347	89.51 394	69.83 383	90.52 272	87.34 364	78.87 336	87.22 363	92.74 318	66.91 358	96.53 324	81.77 304	86.88 404	94.58 344
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_8					96.37 194	89.14 103	90.51 273	96.89 176	79.37 328	90.42 307	94.36 271	91.20 147	98.82 136

test_yl		90.11 248	89.73 253	91.26 255	94.09 304	79.82 273	90.44 274	92.65 310	90.90 141	93.19 239	93.30 303	73.90 329	98.03 230	82.23 300	96.87 279	95.93 295

DCV-MVSNet		90.11 248	89.73 253	91.26 255	94.09 304	79.82 273	90.44 274	92.65 310	90.90 141	93.19 239	93.30 303	73.90 329	98.03 230	82.23 300	96.87 279	95.93 295

tpm2		81.46 364	80.35 371	84.80 373	89.90 387	65.14 403	90.44 274	85.36 383	65.82 408	82.05 401	92.44 325	57.94 395	96.69 322	70.71 392	88.49 401	92.56 382

test_fmvs1		87.59 303	87.27 299	88.54 323	88.32 402	81.26 250	90.43 277	95.72 233	70.55 391	91.70 285	94.63 261	68.13 351	89.42 405	90.59 152	95.34 321	94.94 333

test_vis3_rt		90.40 234	90.03 245	91.52 245	92.58 334	88.95 106	90.38 278	97.72 110	73.30 372	97.79 33	97.51 90	77.05 312	87.10 410	89.03 203	94.89 332	98.50 124

CostFormer		83.09 351	82.21 354	85.73 363	89.27 396	67.01 391	90.35 279	86.47 370	70.42 392	83.52 390	93.23 306	61.18 389	96.85 317	77.21 350	88.26 402	93.34 372

TAMVS		90.16 245	89.05 261	93.49 176	96.49 187	86.37 166	90.34 280	92.55 314	80.84 315	92.99 245	94.57 265	81.94 273	98.20 217	73.51 374	98.21 206	95.90 298

EPMVS		81.17 368	80.37 370	83.58 384	85.58 415	65.08 404	90.31 281	71.34 420	77.31 347	85.80 370	91.30 344	59.38 393	92.70 387	79.99 324	82.34 413	92.96 377

CMPMVS	68.83 22	87.28 310	85.67 326	92.09 225	88.77 400	85.42 191	90.31 281	94.38 276	70.02 394	88.00 351	93.30 303	73.78 331	94.03 378	75.96 361	96.54 291	96.83 254
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_post1							90.21 283				5.85 425	65.36 369	96.00 343	79.61 331

test_prior2							90.21 283		89.33 176	90.77 300	94.81 252	90.41 167		88.21 215	98.55 171

MVS_111021_LR		93.66 148	93.28 165	94.80 110	96.25 211	90.95 73	90.21 283	95.43 248	87.91 206	93.74 217	94.40 268	92.88 109	96.38 332	90.39 158	98.28 197	97.07 241

WR-MVS		93.49 152	93.72 149	92.80 197	97.57 125	80.03 267	90.14 286	95.68 234	93.70 68	96.62 88	95.39 233	87.21 210	99.04 108	87.50 232	99.64 23	99.33 26

tpmrst		82.85 355	82.93 349	82.64 387	87.65 404	58.99 418	90.14 286	87.90 359	75.54 357	83.93 386	91.63 341	66.79 361	95.36 357	81.21 313	81.54 414	93.57 370

PVSNet_BlendedMVS		90.35 239	89.96 246	91.54 244	94.81 282	78.80 299	90.14 286	96.93 171	79.43 327	88.68 342	95.06 243	86.27 227	98.15 223	80.27 319	98.04 222	97.68 206

BH-untuned		90.68 226	90.90 222	90.05 296	95.98 233	79.57 280	90.04 289	94.94 262	87.91 206	94.07 204	93.00 310	87.76 201	97.78 260	79.19 336	95.17 326	92.80 380

新几何2							90.02 290

旧先验2							90.00 291		68.65 399	92.71 256			96.52 325	85.15 267

无先验							89.94 292	95.75 232	70.81 389				98.59 180	81.17 314		94.81 336

xiu_mvs_v1_base_debu		91.47 213	91.52 207	91.33 250	95.69 251	81.56 245	89.92 293	96.05 224	83.22 285	91.26 292	90.74 352	91.55 137	98.82 136	89.29 193	95.91 304	93.62 367

xiu_mvs_v1_base		91.47 213	91.52 207	91.33 250	95.69 251	81.56 245	89.92 293	96.05 224	83.22 285	91.26 292	90.74 352	91.55 137	98.82 136	89.29 193	95.91 304	93.62 367

xiu_mvs_v1_base_debi		91.47 213	91.52 207	91.33 250	95.69 251	81.56 245	89.92 293	96.05 224	83.22 285	91.26 292	90.74 352	91.55 137	98.82 136	89.29 193	95.91 304	93.62 367

mvs_anonymous		90.37 238	91.30 215	87.58 341	92.17 348	68.00 388	89.84 296	94.73 270	83.82 279	93.22 238	97.40 95	87.54 204	97.40 286	87.94 226	95.05 329	97.34 230

test20.03		90.80 222	90.85 225	90.63 278	95.63 256	79.24 287	89.81 297	92.87 304	89.90 164	94.39 195	96.40 171	85.77 231	95.27 361	73.86 373	99.05 106	97.39 227

testing3		83.66 346	82.52 351	87.08 345	95.84 240	65.84 400	89.80 298	77.17 418	88.17 203	90.84 299	88.63 376	30.95 426	98.11 225	84.05 282	97.19 266	97.28 234

WB-MVS		89.44 263	92.15 193	81.32 391	97.73 112	48.22 423	89.73 299	87.98 358	95.24 42	96.05 116	96.99 134	85.18 239	96.95 310	82.45 298	97.97 229	98.78 87

1112_ss		88.42 287	87.41 296	91.45 246	96.69 170	80.99 254	89.72 300	96.72 189	73.37 371	87.00 364	90.69 355	77.38 308	98.20 217	81.38 310	93.72 360	95.15 322

UnsupCasMVSNet_eth		90.33 240	90.34 239	90.28 286	94.64 293	80.24 259	89.69 301	95.88 228	85.77 245	93.94 212	95.69 217	81.99 271	92.98 386	84.21 281	91.30 389	97.62 209

MG-MVS		89.54 260	89.80 250	88.76 318	94.88 278	72.47 368	89.60 302	92.44 316	85.82 244	89.48 326	95.98 201	82.85 260	97.74 266	81.87 303	95.27 323	96.08 288

Patchmatch-test		86.10 326	86.01 323	86.38 359	90.63 377	74.22 354	89.57 303	86.69 368	85.73 247	89.81 321	92.83 314	65.24 371	91.04 394	77.82 345	95.78 309	93.88 360

Anonymous20231206		88.77 280	88.29 278	90.20 291	96.31 204	78.81 298	89.56 304	93.49 295	74.26 367	92.38 269	95.58 223	82.21 267	95.43 356	72.07 382	98.75 151	96.34 274

dmvs_re		84.69 338	83.94 340	86.95 349	92.24 343	82.93 229	89.51 305	87.37 363	84.38 274	85.37 371	85.08 401	72.44 335	86.59 411	68.05 398	91.03 393	91.33 391

DeepPCF-MVS	90.46 6	94.20 133	93.56 158	96.14 55	95.96 234	92.96 47	89.48 306	97.46 130	85.14 260	96.23 106	95.42 229	93.19 97	98.08 227	90.37 160	98.76 149	97.38 229

test_cas_vis1_n_1920		88.25 290	88.27 280	88.20 331	92.19 347	78.92 293	89.45 307	95.44 246	75.29 362	93.23 237	95.65 219	71.58 340	90.23 400	88.05 222	93.55 364	95.44 316

SCA		87.43 307	87.21 301	88.10 333	92.01 353	71.98 370	89.43 308	88.11 356	82.26 300	88.71 340	92.83 314	78.65 294	97.59 274	79.61 331	93.30 368	94.75 340

testgi		90.38 237	91.34 214	87.50 342	97.49 129	71.54 371	89.43 308	95.16 255	88.38 198	94.54 192	94.68 260	92.88 109	93.09 385	71.60 386	97.85 237	97.88 184

JIA-IIPM		85.08 333	83.04 347	91.19 260	87.56 405	86.14 173	89.40 310	84.44 392	88.98 183	82.20 399	97.95 56	56.82 398	96.15 337	76.55 356	83.45 410	91.30 392

原ACMM2							89.34 311

tpm		84.38 340	84.08 337	85.30 369	90.47 381	63.43 409	89.34 311	85.63 379	77.24 348	87.62 358	95.03 244	61.00 391	97.30 290	79.26 335	91.09 392	95.16 321

MVS_111021_HR		93.63 149	93.42 162	94.26 138	96.65 173	86.96 150	89.30 313	96.23 215	88.36 200	93.57 220	94.60 263	93.45 87	97.77 261	90.23 169	98.38 187	98.03 164

tpm cat1		80.61 372	79.46 375	84.07 381	88.78 399	65.06 405	89.26 314	88.23 353	62.27 413	81.90 403	89.66 367	62.70 386	95.29 360	71.72 384	80.60 415	91.86 389

CDS-MVSNet		89.55 259	88.22 284	93.53 172	95.37 269	86.49 161	89.26 314	93.59 291	79.76 322	91.15 295	92.31 328	77.12 311	98.38 201	77.51 347	97.92 233	95.71 305
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+		91.28 218	90.86 224	92.53 211	95.45 265	82.53 233	89.25 316	96.52 203	85.00 264	89.91 318	88.55 378	92.94 105	98.84 134	84.72 277	95.44 317	96.22 282

BH-RMVSNet		90.47 232	90.44 236	90.56 280	95.21 273	78.65 301	89.15 317	93.94 288	88.21 201	92.74 255	94.22 274	86.38 225	97.88 247	78.67 339	95.39 319	95.14 323

thres200		85.85 327	85.18 328	87.88 338	94.44 296	72.52 367	89.08 318	86.21 371	88.57 194	91.44 289	88.40 379	64.22 375	98.00 236	68.35 397	95.88 307	93.12 373

USDC		89.02 271	89.08 260	88.84 317	95.07 275	74.50 349	88.97 319	96.39 208	73.21 373	93.27 233	96.28 184	82.16 269	96.39 331	77.55 346	98.80 144	95.62 312

testdata1							88.96 320		88.44 197

pmmvs5		87.87 295	87.14 303	90.07 293	93.26 321	76.97 325	88.89 321	92.18 319	73.71 370	88.36 346	93.89 288	76.86 318	96.73 321	80.32 318	96.81 282	96.51 264

dmvs_testset		78.23 383	78.99 377	75.94 398	91.99 354	55.34 421	88.86 322	78.70 413	82.69 293	81.64 405	79.46 413	75.93 322	85.74 413	48.78 419	82.85 412	86.76 406

patch_mono-2		92.46 188	92.72 180	91.71 236	96.65 173	78.91 294	88.85 323	97.17 154	83.89 278	92.45 265	96.76 148	89.86 179	97.09 304	90.24 168	98.59 168	99.12 43

test222					96.95 153	85.27 193	88.83 324	93.61 290	65.09 409	90.74 301	94.85 250	84.62 245			97.36 261	93.91 358

baseline2		83.38 349	81.54 359	88.90 315	91.38 367	72.84 365	88.78 325	81.22 404	78.97 334	79.82 410	87.56 384	61.73 388	97.80 256	74.30 370	90.05 396	96.05 290

diffmvs		91.74 205	91.93 199	91.15 261	93.06 324	78.17 306	88.77 326	97.51 128	86.28 233	92.42 267	93.96 285	88.04 196	97.46 281	90.69 151	96.67 288	97.82 193
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MDTV_nov1_ep13			83.88 342		89.42 395	61.52 412	88.74 327	87.41 362	73.99 368	84.96 378	94.01 283	65.25 370	95.53 350	78.02 341	93.16 371

D2MVS		89.93 254	89.60 255	90.92 268	94.03 307	78.40 302	88.69 328	94.85 263	78.96 335	93.08 241	95.09 241	74.57 327	96.94 311	88.19 217	98.96 122	97.41 223

TR-MVS		87.70 298	87.17 302	89.27 310	94.11 303	79.26 286	88.69 328	91.86 328	81.94 303	90.69 303	89.79 363	82.82 261	97.42 284	72.65 380	91.98 386	91.14 393

PatchMatch-RL		89.18 266	88.02 289	92.64 202	95.90 238	92.87 49	88.67 330	91.06 334	80.34 316	90.03 316	91.67 340	83.34 252	94.42 372	76.35 357	94.84 335	90.64 396

PAPR		87.65 301	86.77 312	90.27 287	92.85 331	77.38 317	88.56 331	96.23 215	76.82 352	84.98 377	89.75 365	86.08 229	97.16 301	72.33 381	93.35 367	96.26 280

MDTV_nov1_ep13_2view						42.48 426	88.45 332		67.22 403	83.56 389		66.80 359		72.86 379		94.06 354

WB-MVSnew		84.20 342	83.89 341	85.16 371	91.62 364	66.15 399	88.44 333	81.00 405	76.23 354	87.98 352	87.77 383	84.98 242	93.35 383	62.85 410	94.10 355	95.98 292

jason		89.17 267	88.32 276	91.70 237	95.73 249	80.07 264	88.10 334	93.22 299	71.98 380	90.09 313	92.79 316	78.53 297	98.56 183	87.43 234	97.06 270	96.46 270
jason: jason.
mvsany_test3		89.11 269	88.21 285	91.83 230	91.30 369	90.25 83	88.09 335	78.76 412	76.37 353	96.43 93	98.39 36	83.79 250	90.43 399	86.57 248	94.20 350	94.80 337

BH-w/o		87.21 312	87.02 307	87.79 340	94.77 285	77.27 319	87.90 336	93.21 301	81.74 305	89.99 317	88.39 380	83.47 251	96.93 313	71.29 387	92.43 382	89.15 398

MS-PatchMatch		88.05 293	87.75 291	88.95 314	93.28 319	77.93 308	87.88 337	92.49 315	75.42 358	92.57 261	93.59 297	80.44 283	94.24 377	81.28 311	92.75 377	94.69 343

DELS-MVS		92.05 200	92.16 191	91.72 235	94.44 296	80.13 263	87.62 338	97.25 149	87.34 220	92.22 276	93.18 308	89.54 182	98.73 156	89.67 184	98.20 208	96.30 276
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
ADS-MVSNet2		84.01 343	82.20 355	89.41 306	89.04 397	76.37 333	87.57 339	90.98 336	72.71 378	84.46 380	92.45 323	68.08 352	96.48 327	70.58 393	83.97 408	95.38 317

ADS-MVSNet		82.25 357	81.55 358	84.34 378	89.04 397	65.30 401	87.57 339	85.13 388	72.71 378	84.46 380	92.45 323	68.08 352	92.33 388	70.58 393	83.97 408	95.38 317

IterMVS-SCA-FT		91.65 207	91.55 206	91.94 228	93.89 310	79.22 288	87.56 341	93.51 294	91.53 129	95.37 152	96.62 159	78.65 294	98.90 124	91.89 121	94.95 331	97.70 204

IterMVS		90.18 244	90.16 241	90.21 290	93.15 322	75.98 336	87.56 341	92.97 303	86.43 232	94.09 202	96.40 171	78.32 299	97.43 283	87.87 227	94.69 339	97.23 236
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Test_1112_low_res		87.50 306	86.58 314	90.25 288	96.80 167	77.75 312	87.53 343	96.25 213	69.73 396	86.47 366	93.61 296	75.67 323	97.88 247	79.95 325	93.20 370	95.11 326

c3_l		91.32 217	91.42 211	91.00 266	92.29 342	76.79 327	87.52 344	96.42 207	85.76 246	94.72 189	93.89 288	82.73 262	98.16 222	90.93 146	98.55 171	98.04 161

UnsupCasMVSNet_bld		88.50 285	88.03 288	89.90 298	95.52 262	78.88 295	87.39 345	94.02 285	79.32 331	93.06 242	94.02 282	80.72 282	94.27 375	75.16 365	93.08 374	96.54 262

lupinMVS		88.34 289	87.31 297	91.45 246	94.74 287	80.06 265	87.23 346	92.27 318	71.10 386	88.83 333	91.15 346	77.02 313	98.53 187	86.67 246	96.75 285	95.76 303

pmmvs4		88.95 276	87.70 293	92.70 199	94.30 299	85.60 187	87.22 347	92.16 321	74.62 364	89.75 324	94.19 275	77.97 302	96.41 330	82.71 292	96.36 295	96.09 287

WTY-MVS		86.93 320	86.50 320	88.24 330	94.96 276	74.64 345	87.19 348	92.07 324	78.29 339	88.32 347	91.59 342	78.06 301	94.27 375	74.88 366	93.15 372	95.80 301

ET-MVSNet_ETH3D		86.15 325	84.27 336	91.79 232	93.04 325	81.28 249	87.17 349	86.14 372	79.57 325	83.65 387	88.66 375	57.10 396	98.18 220	87.74 229	95.40 318	95.90 298

MVS-HIRNet		78.83 382	80.60 368	73.51 400	93.07 323	47.37 424	87.10 350	78.00 415	68.94 398	77.53 413	97.26 109	71.45 341	94.62 368	63.28 409	88.74 400	78.55 415

xiu_mvs_v2_base		89.00 274	89.19 258	88.46 327	94.86 280	74.63 346	86.97 351	95.60 236	80.88 313	87.83 354	88.62 377	91.04 152	98.81 141	82.51 297	94.38 344	91.93 387

DPM-MVS		89.35 264	88.40 274	92.18 222	96.13 222	84.20 206	86.96 352	96.15 221	75.40 359	87.36 361	91.55 343	83.30 253	98.01 234	82.17 302	96.62 289	94.32 350

eth_miper_zixun_eth		90.72 224	90.61 232	91.05 262	92.04 352	76.84 326	86.91 353	96.67 192	85.21 258	94.41 194	93.92 286	79.53 288	98.26 213	89.76 182	97.02 272	98.06 158

dp		79.28 380	78.62 380	81.24 392	85.97 414	56.45 419	86.91 353	85.26 386	72.97 376	81.45 406	89.17 374	56.01 400	95.45 355	73.19 377	76.68 416	91.82 390

sss		87.23 311	86.82 310	88.46 327	93.96 308	77.94 307	86.84 355	92.78 308	77.59 343	87.61 359	91.83 337	78.75 293	91.92 390	77.84 343	94.20 350	95.52 315

miper_ehance_all_eth		90.48 231	90.42 237	90.69 276	91.62 364	76.57 330	86.83 356	96.18 219	83.38 281	94.06 205	92.66 321	82.20 268	98.04 229	89.79 181	97.02 272	97.45 220

CLD-MVS		91.82 202	91.41 212	93.04 185	96.37 194	83.65 214	86.82 357	97.29 146	84.65 270	92.27 275	89.67 366	92.20 123	97.85 253	83.95 283	99.47 41	97.62 209
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
cl____		90.65 227	90.56 234	90.91 270	91.85 357	76.98 324	86.75 358	95.36 251	85.53 253	94.06 205	94.89 248	77.36 310	97.98 239	90.27 166	98.98 115	97.76 199

DIV-MVS_self_test		90.65 227	90.56 234	90.91 270	91.85 357	76.99 323	86.75 358	95.36 251	85.52 255	94.06 205	94.89 248	77.37 309	97.99 238	90.28 165	98.97 120	97.76 199

PS-MVSNAJ		88.86 278	88.99 264	88.48 326	94.88 278	74.71 344	86.69 360	95.60 236	80.88 313	87.83 354	87.37 387	90.77 157	98.82 136	82.52 296	94.37 345	91.93 387

PVSNet_Blended		88.74 281	88.16 287	90.46 283	94.81 282	78.80 299	86.64 361	96.93 171	74.67 363	88.68 342	89.18 373	86.27 227	98.15 223	80.27 319	96.00 302	94.44 347

MSDG		90.82 221	90.67 231	91.26 255	94.16 301	83.08 226	86.63 362	96.19 218	90.60 152	91.94 282	91.89 336	89.16 185	95.75 348	80.96 316	94.51 342	94.95 331

cl22		89.02 271	88.50 272	90.59 279	89.76 388	76.45 331	86.62 363	94.03 283	82.98 291	92.65 257	92.49 322	72.05 338	97.53 276	88.93 204	97.02 272	97.78 197

CL-MVSNet_self_test		90.04 253	89.90 248	90.47 281	95.24 272	77.81 311	86.60 364	92.62 312	85.64 249	93.25 236	93.92 286	83.84 249	96.06 341	79.93 327	98.03 223	97.53 216

PCF-MVS	84.52 17	89.12 268	87.71 292	93.34 179	96.06 226	85.84 181	86.58 365	97.31 143	68.46 400	93.61 219	93.89 288	87.51 205	98.52 188	67.85 399	98.11 215	95.66 309
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_f		86.65 323	87.13 304	85.19 370	90.28 384	86.11 174	86.52 366	91.66 330	69.76 395	95.73 134	97.21 116	69.51 348	81.28 417	89.15 200	94.40 343	88.17 403

UWE-MVS		80.29 375	79.10 376	83.87 382	91.97 355	59.56 416	86.50 367	77.43 417	75.40 359	87.79 356	88.10 381	44.08 416	96.90 315	64.23 406	96.36 295	95.14 323

testing91		83.56 348	82.45 352	86.91 350	92.92 329	67.29 389	86.33 368	88.07 357	86.22 235	84.26 383	85.76 396	48.15 409	97.17 299	76.27 358	94.08 356	96.27 279

testing222		80.54 373	78.53 381	86.58 354	92.54 338	68.60 386	86.24 369	82.72 398	83.78 280	82.68 397	84.24 404	39.25 424	95.94 345	60.25 411	95.09 328	95.20 319

Patchmatch-RL test		88.81 279	88.52 271	89.69 303	95.33 271	79.94 270	86.22 370	92.71 309	78.46 338	95.80 127	94.18 276	66.25 364	95.33 359	89.22 198	98.53 174	93.78 361

ETVMVS		79.85 378	77.94 385	85.59 364	92.97 327	66.20 398	86.13 371	80.99 406	81.41 307	83.52 390	83.89 405	41.81 422	94.98 367	56.47 415	94.25 349	95.61 313

testing99		82.94 353	81.72 356	86.59 353	92.55 336	66.53 395	86.08 372	85.70 377	85.47 256	83.95 385	85.70 397	45.87 411	97.07 306	76.58 355	93.56 363	96.17 286

Syy-MVS		84.81 335	84.93 329	84.42 377	91.71 361	63.36 410	85.89 373	81.49 402	81.03 310	85.13 374	81.64 411	77.44 306	95.00 364	85.94 259	94.12 353	94.91 334

myMVS_eth3d		79.62 379	78.26 382	83.72 383	91.71 361	61.25 414	85.89 373	81.49 402	81.03 310	85.13 374	81.64 411	32.12 425	95.00 364	71.17 391	94.12 353	94.91 334

testing11		81.98 362	80.52 369	86.38 359	92.69 333	67.13 390	85.79 375	84.80 389	82.16 301	81.19 407	85.41 399	45.24 412	96.88 316	74.14 371	93.24 369	95.14 323

FPMVS		84.50 339	83.28 345	88.16 332	96.32 203	94.49 20	85.76 376	85.47 382	83.09 288	85.20 373	94.26 272	63.79 379	86.58 412	63.72 408	91.88 388	83.40 410

IB-MVS	77.21 19	83.11 350	81.05 362	89.29 309	91.15 370	75.85 337	85.66 377	86.00 374	79.70 323	82.02 402	86.61 390	48.26 407	98.39 198	77.84 343	92.22 383	93.63 366
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
MDA-MVSNet-bldmvs		91.04 219	90.88 223	91.55 243	94.68 291	80.16 260	85.49 378	92.14 322	90.41 158	94.93 179	95.79 210	85.10 240	96.93 313	85.15 267	94.19 352	97.57 212

test_vis1_rt		85.58 329	84.58 332	88.60 322	87.97 403	86.76 153	85.45 379	93.59 291	66.43 404	87.64 357	89.20 372	79.33 289	85.38 414	81.59 307	89.98 397	93.66 365

new-patchmatchnet		88.97 275	90.79 228	83.50 385	94.28 300	55.83 420	85.34 380	93.56 293	86.18 237	95.47 145	95.73 216	83.10 255	96.51 326	85.40 264	98.06 220	98.16 152

miper_enhance_ethall		88.42 287	87.87 290	90.07 293	88.67 401	75.52 340	85.10 381	95.59 240	75.68 355	92.49 262	89.45 369	78.96 291	97.88 247	87.86 228	97.02 272	96.81 255

HyFIR lowres test		87.19 314	85.51 327	92.24 217	97.12 149	80.51 258	85.03 382	96.06 222	66.11 406	91.66 286	92.98 312	70.12 346	99.14 93	75.29 364	95.23 324	97.07 241

pmmvs3		80.83 370	78.96 378	86.45 356	87.23 408	77.48 316	84.87 383	82.31 399	63.83 411	85.03 376	89.50 368	49.66 406	93.10 384	73.12 378	95.10 327	88.78 402

test0.0.03 1		82.48 356	81.47 360	85.48 367	89.70 389	73.57 358	84.73 384	81.64 401	83.07 289	88.13 350	86.61 390	62.86 384	89.10 407	66.24 403	90.29 395	93.77 362

N_pmnet		88.90 277	87.25 300	93.83 157	94.40 298	93.81 39	84.73 384	87.09 365	79.36 330	93.26 234	92.43 326	79.29 290	91.68 391	77.50 348	97.22 265	96.00 291

GA-MVS		87.70 298	86.82 310	90.31 285	93.27 320	77.22 320	84.72 386	92.79 307	85.11 262	89.82 320	90.07 358	66.80 359	97.76 263	84.56 278	94.27 348	95.96 293

ppachtmachnet_test		88.61 284	88.64 270	88.50 325	91.76 359	70.99 375	84.59 387	92.98 302	79.30 332	92.38 269	93.53 299	79.57 287	97.45 282	86.50 252	97.17 267	97.07 241

CHOSEN 1792x2688		87.19 314	85.92 325	91.00 266	97.13 148	79.41 283	84.51 388	95.60 236	64.14 410	90.07 315	94.81 252	78.26 300	97.14 302	73.34 375	95.38 320	96.46 270

thisisatest0515		84.72 337	82.99 348	89.90 298	92.96 328	75.33 342	84.36 389	83.42 395	77.37 345	88.27 348	86.65 389	53.94 402	98.72 157	82.56 295	97.40 260	95.67 308

cascas		87.02 319	86.28 322	89.25 311	91.56 366	76.45 331	84.33 390	96.78 184	71.01 387	86.89 365	85.91 395	81.35 276	96.94 311	83.09 289	95.60 312	94.35 349

new_pmnet		81.22 366	81.01 364	81.86 389	90.92 374	70.15 378	84.03 391	80.25 410	70.83 388	85.97 369	89.78 364	67.93 355	84.65 415	67.44 400	91.90 387	90.78 395

PAPM		81.91 363	80.11 373	87.31 344	93.87 311	72.32 369	84.02 392	93.22 299	69.47 397	76.13 415	89.84 360	72.15 337	97.23 294	53.27 417	89.02 399	92.37 384

UBG		80.28 376	78.94 379	84.31 379	92.86 330	61.77 411	83.87 393	83.31 397	77.33 346	82.78 396	83.72 406	47.60 410	96.06 341	65.47 405	93.48 365	95.11 326

our_test_3		87.55 304	87.59 294	87.44 343	91.76 359	70.48 376	83.83 394	90.55 341	79.79 321	92.06 281	92.17 331	78.63 296	95.63 349	84.77 275	94.73 337	96.22 282

WBMVS		84.00 344	83.48 343	85.56 365	92.71 332	61.52 412	83.82 395	89.38 346	79.56 326	90.74 301	93.20 307	48.21 408	97.28 291	75.63 363	98.10 217	97.88 184

miper_lstm_enhance		89.90 255	89.80 250	90.19 292	91.37 368	77.50 315	83.82 395	95.00 259	84.84 268	93.05 243	94.96 246	76.53 321	95.20 362	89.96 178	98.67 161	97.86 187

test-LLR		83.58 347	83.17 346	84.79 374	89.68 390	66.86 393	83.08 397	84.52 390	83.07 289	82.85 394	84.78 402	62.86 384	93.49 381	82.85 290	94.86 333	94.03 355

TESTMET0.1,1		79.09 381	78.04 383	82.25 388	87.52 406	64.03 408	83.08 397	80.62 408	70.28 393	80.16 409	83.22 408	44.13 415	90.56 397	79.95 325	93.36 366	92.15 385

test-mter		81.21 367	80.01 374	84.79 374	89.68 390	66.86 393	83.08 397	84.52 390	73.85 369	82.85 394	84.78 402	43.66 417	93.49 381	82.85 290	94.86 333	94.03 355

test123		9.49 391	12.01 394	1.91 406	2.87 429	1.30 431	82.38 400	1.34 431	1.36 424	2.84 425	6.56 423	2.45 429	0.97 425	2.73 424	5.56 423	3.47 421

PMMVS		83.00 352	81.11 361	88.66 321	83.81 420	86.44 164	82.24 401	85.65 378	61.75 414	82.07 400	85.64 398	79.75 286	91.59 392	75.99 360	93.09 373	87.94 404

KD-MVS_2432*1600		82.17 359	80.75 366	86.42 357	82.04 421	70.09 379	81.75 402	90.80 338	82.56 294	90.37 309	89.30 370	42.90 419	96.11 339	74.47 368	92.55 380	93.06 374

miper_refine_blended		82.17 359	80.75 366	86.42 357	82.04 421	70.09 379	81.75 402	90.80 338	82.56 294	90.37 309	89.30 370	42.90 419	96.11 339	74.47 368	92.55 380	93.06 374

mvsany_test1		83.91 345	82.93 349	86.84 352	86.18 413	85.93 178	81.11 404	75.03 419	70.80 390	88.57 344	94.63 261	83.08 256	87.38 409	80.39 317	86.57 405	87.21 405

YYNet1		88.17 291	88.24 282	87.93 335	92.21 345	73.62 357	80.75 405	88.77 348	82.51 297	94.99 177	95.11 240	82.70 263	93.70 379	83.33 286	93.83 358	96.48 268

MDA-MVSNet_test_wron		88.16 292	88.23 283	87.93 335	92.22 344	73.71 356	80.71 406	88.84 347	82.52 296	94.88 182	95.14 238	82.70 263	93.61 380	83.28 287	93.80 359	96.46 270

testmvs		9.02 392	11.42 395	1.81 407	2.77 430	1.13 432	79.44 407	1.90 430	1.18 425	2.65 426	6.80 422	1.95 430	0.87 426	2.62 425	3.45 424	3.44 422

PVSNet	76.22 20	82.89 354	82.37 353	84.48 376	93.96 308	64.38 407	78.60 408	88.61 349	71.50 383	84.43 382	86.36 393	74.27 328	94.60 369	69.87 395	93.69 361	94.46 346

dongtai		53.72 386	53.79 389	53.51 403	79.69 423	36.70 427	77.18 409	32.53 429	71.69 381	68.63 419	60.79 418	26.65 427	73.11 419	30.67 422	36.29 421	50.73 417

kuosan		43.63 388	44.25 392	41.78 404	66.04 426	34.37 428	75.56 410	32.62 428	53.25 419	50.46 422	51.18 419	25.28 428	49.13 422	13.44 423	30.41 422	41.84 419

PVSNet_0	70.34 21	74.58 384	72.96 387	79.47 395	90.63 377	66.24 397	73.26 411	83.40 396	63.67 412	78.02 412	78.35 415	72.53 334	89.59 403	56.68 414	60.05 419	82.57 413

E-PMN		80.72 371	80.86 365	80.29 394	85.11 416	68.77 385	72.96 412	81.97 400	87.76 212	83.25 393	83.01 409	62.22 387	89.17 406	77.15 351	94.31 347	82.93 411

CHOSEN 280x420		80.04 377	77.97 384	86.23 361	90.13 385	74.53 348	72.87 413	89.59 345	66.38 405	76.29 414	85.32 400	56.96 397	95.36 357	69.49 396	94.72 338	88.79 401

EMVS		80.35 374	80.28 372	80.54 393	84.73 418	69.07 384	72.54 414	80.73 407	87.80 210	81.66 404	81.73 410	62.89 383	89.84 401	75.79 362	94.65 340	82.71 412

PMMVS2		81.31 365	83.44 344	74.92 399	90.52 379	46.49 425	69.19 415	85.23 387	84.30 275	87.95 353	94.71 258	76.95 315	84.36 416	64.07 407	98.09 218	93.89 359

tmp_tt		37.97 389	44.33 391	18.88 405	11.80 428	21.54 429	63.51 416	45.66 427	4.23 422	51.34 421	50.48 420	59.08 394	22.11 424	44.50 420	68.35 418	13.00 420

MVE	59.87 23	73.86 385	72.65 388	77.47 397	87.00 411	74.35 350	61.37 417	60.93 423	67.27 402	69.69 418	86.49 392	81.24 280	72.33 420	56.45 416	83.45 410	85.74 408
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.44 387	48.94 390	54.93 401	39.68 427	12.38 430	28.59 418	90.09 342	6.82 421	41.10 423	78.41 414	54.41 401	70.69 421	50.12 418	51.26 420	81.72 414

mmdepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

cdsmvs_eth3d_5k		23.35 390	31.13 393	0.00 408	0.00 431	0.00 433	0.00 419	95.58 242	0.00 426	0.00 427	91.15 346	93.43 89	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		7.56 393	10.09 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	90.77 157	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

ab-mvs-re		7.56 393	10.08 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	90.69 355	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						61.25 414								74.55 367

MSC_two_6792asdad				95.90 67	96.54 182	89.57 91		96.87 178					99.41 42	94.06 49	99.30 72	98.72 96

PC_three_1452									75.31 361	95.87 125	95.75 215	92.93 106	96.34 336	87.18 238	98.68 159	98.04 161

No_MVS				95.90 67	96.54 182	89.57 91		96.87 178					99.41 42	94.06 49	99.30 72	98.72 96

test_one_0601					98.26 71	87.14 143		98.18 49	94.25 55	96.99 71	97.36 100	95.13 45

eth-test2					0.00 431

eth-test					0.00 431

ZD-MVS					97.23 141	90.32 82		97.54 123	84.40 273	94.78 185	95.79 210	92.76 112	99.39 52	88.72 211	98.40 183

IU-MVS					98.51 49	86.66 158		96.83 181	72.74 377	95.83 126				93.00 92	99.29 75	98.64 111

test_241102_TWO								98.10 63	91.95 104	97.54 43	97.25 110	95.37 32	99.35 62	93.29 80	99.25 83	98.49 126

test_241102_ONE					98.51 49	86.97 148		98.10 63	91.85 110	97.63 38	97.03 130	96.48 10	98.95 120

test_0728_THIRD									93.26 78	97.40 54	97.35 103	94.69 63	99.34 65	93.88 53	99.42 50	98.89 75

GSMVS																94.75 340

test_part2					98.21 76	89.41 96				96.72 83

sam_mvs1												66.64 362				94.75 340

sam_mvs												66.41 363

MTGPA								97.62 115

test_post											6.07 424	65.74 367	95.84 347

patchmatchnet-post											91.71 339	66.22 365	97.59 274

gm-plane-assit					87.08 410	59.33 417			71.22 384		83.58 407		97.20 296	73.95 372

test9_res														88.16 219	98.40 183	97.83 191

agg_prior2														87.06 241	98.36 192	97.98 170

agg_prior					96.20 214	88.89 108		96.88 177		90.21 312			98.78 148

TestCases				96.00 58	98.02 90	92.17 54		98.43 21	90.48 154	95.04 174	96.74 151	92.54 116	97.86 251	85.11 270	98.98 115	97.98 170

test_prior				94.61 120	95.95 235	87.23 140		97.36 139					98.68 168			97.93 177

新几何1				93.17 184	97.16 146	87.29 138		94.43 275	67.95 401	91.29 291	94.94 247	86.97 216	98.23 215	81.06 315	97.75 240	93.98 357

旧先验1					96.20 214	84.17 207		94.82 265			95.57 224	89.57 181			97.89 234	96.32 275

原ACMM1				92.87 194	96.91 157	84.22 205		97.01 165	76.84 351	89.64 325	94.46 267	88.00 197	98.70 164	81.53 309	98.01 226	95.70 307

testdata2													98.03 230	80.24 321

segment_acmp												92.14 124

testdata				91.03 263	96.87 160	82.01 239		94.28 279	71.55 382	92.46 264	95.42 229	85.65 234	97.38 289	82.64 293	97.27 263	93.70 364

test12				94.43 133	95.95 235	86.75 154		96.24 214		89.76 323		89.79 180	98.79 145		97.95 231	97.75 201

plane_prior7					97.71 114	88.68 111

plane_prior6					97.21 144	88.23 124						86.93 217

plane_prior5								97.81 101					98.95 120	89.26 196	98.51 177	98.60 116

plane_prior4											95.59 220

plane_prior3						88.43 122			90.35 159	93.31 229

plane_prior1					97.38 134

n2								0.00 432

nn								0.00 432

door-mid								92.13 323

lessismore_v0				93.87 154	98.05 86	83.77 213		80.32 409		97.13 62	97.91 62	77.49 305	99.11 98	92.62 102	98.08 219	98.74 94

LGP-MVS_train				96.84 42	98.36 66	92.13 56		98.25 37	91.78 117	97.07 64	97.22 114	96.38 12	99.28 78	92.07 115	99.59 27	99.11 44

test11								96.65 193

door								91.26 333

HQP5-MVS						84.89 196

BP-MVS														86.55 250

HQP4-MVS										88.81 335			98.61 176			98.15 153

HQP3-MVS								97.31 143							97.73 241

HQP2-MVS												84.76 243

NP-MVS					96.82 165	87.10 144					93.40 301

ACMMP++_ref															98.82 141

ACMMP++															99.25 83

Test By Simon												90.61 163

ITE_SJBPF				95.95 61	97.34 137	93.36 44		96.55 202	91.93 106	94.82 183	95.39 233	91.99 126	97.08 305	85.53 263	97.96 230	97.41 223

DeepMVS_CX				53.83 402	70.38 425	64.56 406		48.52 426	33.01 420	65.50 420	74.21 417	56.19 399	46.64 423	38.45 421	70.07 417	50.30 418

High-resolution multi-view benchmark