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.

mamv4		98.21 2	97.86 3	99.26 1	98.24 71	99.36 1	96.10 63	99.32 2	98.75 2	99.58 2	98.70 18	91.78 128	99.88 1	98.60 1	99.67 20	98.54 117

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 1

PMVS	87.21 14	94.97 94	95.33 87	93.91 148	98.97 17	97.16 3	95.54 89	95.85 225	96.47 25	93.40 220	97.46 86	95.31 35	95.47 345	86.18 249	98.78 144	89.11 387
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testf1		96.77 15	96.49 28	97.60 9	99.01 14	96.70 4	96.31 52	98.33 24	94.96 41	97.30 54	97.93 55	96.05 16	97.90 238	89.32 181	99.23 84	98.19 141

APD_test2		96.77 15	96.49 28	97.60 9	99.01 14	96.70 4	96.31 52	98.33 24	94.96 41	97.30 54	97.93 55	96.05 16	97.90 238	89.32 181	99.23 84	98.19 141

Effi-MVS+-dtu		93.90 140	92.60 179	97.77 4	94.74 282	96.67 6	94.00 145	95.41 244	89.94 157	91.93 274	92.13 321	90.12 169	98.97 113	87.68 222	97.48 248	97.67 196

APD_test1		95.91 54	95.42 83	97.36 24	98.82 25	96.62 7	95.64 83	97.64 107	93.38 72	95.89 120	97.23 105	93.35 89	97.66 266	88.20 208	98.66 159	97.79 185

RPSCF		95.58 68	94.89 103	97.62 8	97.58 122	96.30 8	95.97 70	97.53 120	92.42 85	93.41 218	97.78 63	91.21 143	97.77 256	91.06 134	97.06 263	98.80 83

TDRefinement		97.68 4	97.60 5	97.93 3	99.02 12	95.95 9	98.61 3	98.81 10	97.41 11	97.28 56	98.46 32	94.62 64	98.84 130	94.64 34	99.53 37	98.99 54

SR-MVS-dyc-post		96.84 8	96.60 26	97.56 11	98.07 81	95.27 10	96.37 46	98.12 55	95.66 36	97.00 67	97.03 123	94.85 58	99.42 34	93.49 62	98.84 131	98.00 158

RE-MVS-def			96.66 21		98.07 81	95.27 10	96.37 46	98.12 55	95.66 36	97.00 67	97.03 123	95.40 29		93.49 62	98.84 131	98.00 158

SR-MVS		96.70 20	96.42 31	97.54 12	98.05 83	94.69 12	96.13 62	98.07 64	95.17 40	96.82 76	96.73 147	95.09 47	99.43 33	92.99 88	98.71 151	98.50 120

FOURS1					99.21 3	94.68 13	98.45 4	98.81 10	97.73 7	98.27 22

mPP-MVS		96.46 32	96.05 53	97.69 5	98.62 35	94.65 14	96.45 41	97.74 102	92.59 83	95.47 141	96.68 150	94.50 68	99.42 34	93.10 83	99.26 80	98.99 54

CP-MVS		96.44 35	96.08 51	97.54 12	98.29 65	94.62 15	96.80 24	98.08 61	92.67 82	95.08 168	96.39 169	94.77 60	99.42 34	93.17 81	99.44 48	98.58 116

EGC-MVSNET		80.97 358	75.73 374	96.67 43	98.85 23	94.55 16	96.83 22	96.60 190	2.44 411	5.32 412	98.25 39	92.24 117	98.02 229	91.85 115	99.21 88	97.45 209

FPMVS		84.50 329	83.28 334	88.16 326	96.32 197	94.49 17	85.76 366	85.47 371	83.09 280	85.20 362	94.26 262	63.79 372	86.58 400	63.72 396	91.88 377	83.40 398

COLMAP_ROB	91.06 5	96.75 17	96.62 24	97.13 29	98.38 60	94.31 18	96.79 25	98.32 26	96.69 20	96.86 74	97.56 75	95.48 27	98.77 147	90.11 165	99.44 48	98.31 132
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
XVG-OURS		94.72 104	94.12 135	96.50 48	98.00 89	94.23 19	91.48 238	98.17 49	90.72 141	95.30 152	96.47 159	87.94 195	96.98 301	91.41 130	97.61 243	98.30 133

LS3D		96.11 48	95.83 66	96.95 37	94.75 281	94.20 20	97.34 12	97.98 79	97.31 12	95.32 151	96.77 139	93.08 99	99.20 83	91.79 117	98.16 206	97.44 211

XVG-OURS-SEG-HR		95.38 78	95.00 101	96.51 47	98.10 79	94.07 21	92.46 197	98.13 54	90.69 142	93.75 210	96.25 182	98.03 2	97.02 300	92.08 107	95.55 303	98.45 125

MP-MVS		96.14 47	95.68 72	97.51 14	98.81 27	94.06 22	96.10 63	97.78 100	92.73 79	93.48 217	96.72 148	94.23 73	99.42 34	91.99 110	99.29 73	99.05 49
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PM-MVS		93.33 153	92.67 177	95.33 85	96.58 175	94.06 22	92.26 211	92.18 312	85.92 234	96.22 104	96.61 154	85.64 232	95.99 335	90.35 153	98.23 199	95.93 285

MSP-MVS		95.34 80	94.63 118	97.48 15	98.67 32	94.05 24	96.41 45	98.18 45	91.26 129	95.12 164	95.15 229	86.60 221	99.50 23	93.43 71	96.81 275	98.89 73
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
MTAPA		96.65 23	96.38 35	97.47 16	98.95 18	94.05 24	95.88 74	97.62 109	94.46 50	96.29 98	96.94 129	93.56 81	99.37 58	94.29 41	99.42 50	98.99 54

anonymousdsp		96.74 18	96.42 31	97.68 7	98.00 89	94.03 26	96.97 19	97.61 111	87.68 208	98.45 20	98.77 15	94.20 74	99.50 23	96.70 6	99.40 55	99.53 14

XVS		96.49 30	96.18 44	97.44 17	98.56 41	93.99 27	96.50 38	97.95 84	94.58 46	94.38 191	96.49 158	94.56 66	99.39 50	93.57 58	99.05 104	98.93 66

X-MVStestdata		90.70 219	88.45 266	97.44 17	98.56 41	93.99 27	96.50 38	97.95 84	94.58 46	94.38 191	26.89 409	94.56 66	99.39 50	93.57 58	99.05 104	98.93 66

HPM-MVS_fast		97.01 7	96.89 15	97.39 22	99.12 8	93.92 29	97.16 14	98.17 49	93.11 76	96.48 89	97.36 93	96.92 6	99.34 63	94.31 40	99.38 57	98.92 70

ACMMP		96.61 25	96.34 36	97.43 19	98.61 37	93.88 30	96.95 20	98.18 45	92.26 92	96.33 94	96.84 137	95.10 46	99.40 47	93.47 65	99.33 65	99.02 51
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
UA-Net		97.35 5	97.24 12	97.69 5	98.22 72	93.87 31	98.42 6	98.19 43	96.95 17	95.46 143	99.23 4	93.45 84	99.57 16	95.34 29	99.89 2	99.63 9

LTVRE_ROB	93.87 1	97.93 3	98.16 2	97.26 27	98.81 27	93.86 32	99.07 2	98.98 7	97.01 16	98.92 6	98.78 14	95.22 40	98.61 172	96.85 4	99.77 9	99.31 26
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
PGM-MVS		96.32 41	95.94 57	97.43 19	98.59 40	93.84 33	95.33 94	98.30 29	91.40 127	95.76 125	96.87 134	95.26 37	99.45 29	92.77 91	99.21 88	99.00 52

APD-MVS_3200maxsize		96.82 10	96.65 22	97.32 26	97.95 93	93.82 34	96.31 52	98.25 33	95.51 38	96.99 69	97.05 122	95.63 23	99.39 50	93.31 74	98.88 126	98.75 89

ACMMPR		96.46 32	96.14 47	97.41 21	98.60 38	93.82 34	96.30 56	97.96 82	92.35 89	95.57 136	96.61 154	94.93 56	99.41 40	93.78 52	99.15 96	99.00 52

region2R		96.41 37	96.09 49	97.38 23	98.62 35	93.81 36	96.32 51	97.96 82	92.26 92	95.28 155	96.57 156	95.02 50	99.41 40	93.63 56	99.11 99	98.94 64

N_pmnet		88.90 271	87.25 293	93.83 153	94.40 293	93.81 36	84.73 374	87.09 356	79.36 320	93.26 226	92.43 315	79.29 287	91.68 381	77.50 338	97.22 258	96.00 281

HPM-MVS++		95.02 92	94.39 122	96.91 38	97.88 97	93.58 38	94.09 143	96.99 163	91.05 134	92.40 259	95.22 228	91.03 150	99.25 77	92.11 105	98.69 154	97.90 171

HPM-MVS		96.81 12	96.62 24	97.36 24	98.89 20	93.53 39	97.51 10	98.44 18	92.35 89	95.95 115	96.41 164	96.71 8	99.42 34	93.99 47	99.36 59	99.13 39
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
HFP-MVS		96.39 39	96.17 46	97.04 32	98.51 49	93.37 40	96.30 56	97.98 79	92.35 89	95.63 133	96.47 159	95.37 30	99.27 75	93.78 52	99.14 97	98.48 123

ITE_SJBPF				95.95 58	97.34 135	93.36 41		96.55 197	91.93 101	94.82 178	95.39 225	91.99 123	97.08 297	85.53 255	97.96 224	97.41 212

XVG-ACMP-BASELINE		95.68 64	95.34 86	96.69 42	98.40 58	93.04 42	94.54 128	98.05 68	90.45 150	96.31 96	96.76 141	92.91 104	98.72 153	91.19 132	99.42 50	98.32 130

CPTT-MVS		94.74 103	94.12 135	96.60 44	98.15 76	93.01 43	95.84 75	97.66 106	89.21 174	93.28 224	95.46 218	88.89 182	98.98 109	89.80 172	98.82 137	97.80 184

DeepPCF-MVS	90.46 6	94.20 129	93.56 154	96.14 52	95.96 228	92.96 44	89.48 296	97.46 125	85.14 251	96.23 103	95.42 221	93.19 94	98.08 223	90.37 152	98.76 146	97.38 218

ACMM	88.83 9	96.30 43	96.07 52	96.97 35	98.39 59	92.95 45	94.74 116	98.03 73	90.82 139	97.15 59	96.85 135	96.25 14	99.00 108	93.10 83	99.33 65	98.95 63
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PatchMatch-RL		89.18 260	88.02 282	92.64 195	95.90 232	92.87 46	88.67 320	91.06 326	80.34 308	90.03 306	91.67 329	83.34 249	94.42 362	76.35 347	94.84 325	90.64 384

ZNCC-MVS		96.42 36	96.20 43	97.07 31	98.80 29	92.79 47	96.08 65	98.16 52	91.74 116	95.34 150	96.36 172	95.68 21	99.44 30	94.41 38	99.28 78	98.97 60

GST-MVS		96.24 44	95.99 56	97.00 34	98.65 33	92.71 48	95.69 81	98.01 76	92.08 97	95.74 128	96.28 178	95.22 40	99.42 34	93.17 81	99.06 101	98.88 75

mvs_tets		96.83 9	96.71 20	97.17 28	98.83 24	92.51 49	96.58 33	97.61 111	87.57 210	98.80 9	98.90 9	96.50 9	99.59 15	96.15 13	99.47 41	99.40 20

jajsoiax		96.59 28	96.42 31	97.12 30	98.76 30	92.49 50	96.44 43	97.42 127	86.96 219	98.71 12	98.72 17	95.36 32	99.56 19	95.92 14	99.45 45	99.32 25

AllTest		94.88 98	94.51 120	96.00 55	98.02 87	92.17 51	95.26 97	98.43 19	90.48 148	95.04 169	96.74 145	92.54 113	97.86 246	85.11 262	98.98 112	97.98 162

TestCases				96.00 55	98.02 87	92.17 51		98.43 19	90.48 148	95.04 169	96.74 145	92.54 113	97.86 246	85.11 262	98.98 112	97.98 162

LPG-MVS_test		96.38 40	96.23 41	96.84 39	98.36 63	92.13 53	95.33 94	98.25 33	91.78 112	97.07 62	97.22 107	96.38 12	99.28 73	92.07 108	99.59 27	99.11 42

LGP-MVS_train				96.84 39	98.36 63	92.13 53		98.25 33	91.78 112	97.07 62	97.22 107	96.38 12	99.28 73	92.07 108	99.59 27	99.11 42

LF4IMVS		92.72 176	92.02 192	94.84 105	95.65 249	91.99 55	92.92 178	96.60 190	85.08 254	92.44 257	93.62 285	86.80 217	96.35 326	86.81 234	98.25 197	96.18 274

SteuartSystems-ACMMP		96.40 38	96.30 38	96.71 41	98.63 34	91.96 56	95.70 79	98.01 76	93.34 73	96.64 84	96.57 156	94.99 52	99.36 59	93.48 64	99.34 63	98.82 80
Skip Steuart: Steuart Systems R&D Blog.
F-COLMAP		92.28 191	91.06 216	95.95 58	97.52 125	91.90 57	93.53 159	97.18 148	83.98 267	88.70 330	94.04 270	88.41 186	98.55 181	80.17 313	95.99 294	97.39 216

OurMVSNet-221017-0		96.80 13	96.75 18	96.96 36	99.03 11	91.85 58	97.98 7	98.01 76	94.15 54	98.93 5	99.07 5	88.07 191	99.57 16	95.86 15	99.69 14	99.46 17

MAR-MVS		90.32 235	88.87 261	94.66 115	94.82 276	91.85 58	94.22 137	94.75 263	80.91 304	87.52 349	88.07 371	86.63 220	97.87 245	76.67 343	96.21 290	94.25 340
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
test_djsdf		96.62 24	96.49 28	97.01 33	98.55 44	91.77 60	97.15 15	97.37 129	88.98 177	98.26 24	98.86 10	93.35 89	99.60 11	96.41 9	99.45 45	99.66 6

ACMP	88.15 13	95.71 63	95.43 82	96.54 46	98.17 75	91.73 61	94.24 135	98.08 61	89.46 166	96.61 86	96.47 159	95.85 18	99.12 92	90.45 148	99.56 34	98.77 88
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CS-MVS		95.77 60	95.58 76	96.37 51	96.84 160	91.72 62	96.73 28	99.06 6	94.23 52	92.48 254	94.79 246	93.56 81	99.49 26	93.47 65	99.05 104	97.89 173

PHI-MVS		94.34 122	93.80 142	95.95 58	95.65 249	91.67 63	94.82 114	97.86 89	87.86 202	93.04 236	94.16 267	91.58 133	98.78 144	90.27 158	98.96 119	97.41 212

ACMMP_NAP		96.21 45	96.12 48	96.49 49	98.90 19	91.42 64	94.57 124	98.03 73	90.42 151	96.37 92	97.35 96	95.68 21	99.25 77	94.44 37	99.34 63	98.80 83

OMC-MVS		94.22 128	93.69 147	95.81 68	97.25 138	91.27 65	92.27 210	97.40 128	87.10 218	94.56 186	95.42 221	93.74 79	98.11 221	86.62 239	98.85 130	98.06 150

MP-MVS-pluss		96.08 49	95.92 60	96.57 45	99.06 10	91.21 66	93.25 168	98.32 26	87.89 201	96.86 74	97.38 89	95.55 26	99.39 50	95.47 22	99.47 41	99.11 42
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SMA-MVS		95.77 60	95.54 77	96.47 50	98.27 67	91.19 67	95.09 104	97.79 99	86.48 222	97.42 50	97.51 83	94.47 71	99.29 71	93.55 60	99.29 73	98.93 66
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
CNLPA		91.72 201	91.20 212	93.26 175	96.17 210	91.02 68	91.14 245	95.55 238	90.16 155	90.87 289	93.56 288	86.31 223	94.40 363	79.92 319	97.12 261	94.37 337

OPM-MVS		95.61 66	95.45 80	96.08 54	98.49 56	91.00 69	92.65 189	97.33 137	90.05 156	96.77 79	96.85 135	95.04 48	98.56 179	92.77 91	99.06 101	98.70 98
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MVS_111021_LR		93.66 144	93.28 161	94.80 106	96.25 205	90.95 70	90.21 273	95.43 243	87.91 199	93.74 212	94.40 258	92.88 106	96.38 324	90.39 150	98.28 193	97.07 230

Gipuma		95.31 84	95.80 68	93.81 154	97.99 92	90.91 71	96.42 44	97.95 84	96.69 20	91.78 275	98.85 12	91.77 129	95.49 344	91.72 119	99.08 100	95.02 318
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
APD-MVS		95.00 93	94.69 112	95.93 61	97.38 132	90.88 72	94.59 121	97.81 95	89.22 173	95.46 143	96.17 187	93.42 87	99.34 63	89.30 183	98.87 129	97.56 203
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + GP.		93.07 164	92.41 183	95.06 98	95.82 237	90.87 73	90.97 249	92.61 306	88.04 198	94.61 185	93.79 281	88.08 190	97.81 250	89.41 180	98.39 182	96.50 256

3Dnovator+	92.74 2	95.86 58	95.77 69	96.13 53	96.81 163	90.79 74	96.30 56	97.82 94	96.13 29	94.74 182	97.23 105	91.33 138	99.16 86	93.25 78	98.30 192	98.46 124

CS-MVS-test		95.32 81	95.10 97	95.96 57	96.86 158	90.75 75	96.33 49	99.20 3	93.99 56	91.03 288	93.73 282	93.52 83	99.55 20	91.81 116	99.45 45	97.58 200

hse-mvs2		92.24 193	91.20 212	95.38 82	96.16 211	90.65 76	92.52 193	92.01 319	89.23 171	93.95 205	92.99 300	76.88 312	98.69 162	91.02 135	96.03 292	96.81 244

h-mvs33		92.89 168	91.99 193	95.58 76	96.97 150	90.55 77	93.94 148	94.01 280	89.23 171	93.95 205	96.19 184	76.88 312	99.14 89	91.02 135	95.71 300	97.04 234

AUN-MVS		90.05 246	88.30 270	95.32 87	96.09 218	90.52 78	92.42 201	92.05 318	82.08 294	88.45 334	92.86 302	65.76 361	98.69 162	88.91 198	96.07 291	96.75 248

ZD-MVS					97.23 139	90.32 79		97.54 118	84.40 264	94.78 180	95.79 202	92.76 109	99.39 50	88.72 203	98.40 179

mvsany_test3		89.11 263	88.21 278	91.83 224	91.30 361	90.25 80	88.09 325	78.76 400	76.37 341	96.43 90	98.39 35	83.79 247	90.43 388	86.57 240	94.20 340	94.80 326

DeepC-MVS	91.39 4	95.43 74	95.33 87	95.71 73	97.67 117	90.17 81	93.86 150	98.02 75	87.35 212	96.22 104	97.99 53	94.48 70	99.05 101	92.73 94	99.68 17	97.93 168
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PLC	85.34 15	90.40 228	88.92 258	94.85 104	96.53 182	90.02 82	91.58 236	96.48 200	80.16 310	86.14 357	92.18 319	85.73 229	98.25 210	76.87 342	94.61 331	96.30 265
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_prior4						89.91 83	90.74 255

NCCC		94.08 133	93.54 155	95.70 74	96.49 184	89.90 84	92.39 203	96.91 170	90.64 144	92.33 265	94.60 253	90.58 162	98.96 114	90.21 162	97.70 237	98.23 137

DPE-MVS		95.89 56	95.88 62	95.92 63	97.93 94	89.83 85	93.46 162	98.30 29	92.37 87	97.75 33	96.95 128	95.14 42	99.51 22	91.74 118	99.28 78	98.41 127
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TAPA-MVS	88.58 10	92.49 184	91.75 200	94.73 109	96.50 183	89.69 86	92.91 179	97.68 105	78.02 331	92.79 244	94.10 268	90.85 152	97.96 235	84.76 268	98.16 206	96.54 251
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SF-MVS		95.88 57	95.88 62	95.87 67	98.12 77	89.65 87	95.58 87	98.56 16	91.84 108	96.36 93	96.68 150	94.37 72	99.32 69	92.41 102	99.05 104	98.64 109

MSC_two_6792asdad				95.90 64	96.54 179	89.57 88		96.87 173					99.41 40	94.06 45	99.30 70	98.72 94

No_MVS				95.90 64	96.54 179	89.57 88		96.87 173					99.41 40	94.06 45	99.30 70	98.72 94

TEST9					96.45 187	89.46 90	90.60 260	96.92 168	79.09 323	90.49 295	94.39 259	91.31 139	98.88 123

train_agg		92.71 177	91.83 198	95.35 83	96.45 187	89.46 90	90.60 260	96.92 168	79.37 318	90.49 295	94.39 259	91.20 144	98.88 123	88.66 204	98.43 178	97.72 192

OPU-MVS				95.15 96	96.84 160	89.43 92	95.21 99				95.66 210	93.12 97	98.06 224	86.28 248	98.61 161	97.95 166

test_part2					98.21 73	89.41 93				96.72 80

Vis-MVSNet		95.50 71	95.48 79	95.56 78	98.11 78	89.40 94	95.35 92	98.22 40	92.36 88	94.11 196	98.07 45	92.02 122	99.44 30	93.38 73	97.67 239	97.85 178
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
APDe-MVS		96.46 32	96.64 23	95.93 61	97.68 116	89.38 95	96.90 21	98.41 21	92.52 84	97.43 48	97.92 58	95.11 45	99.50 23	94.45 36	99.30 70	98.92 70
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CNVR-MVS		94.58 111	94.29 127	95.46 81	96.94 152	89.35 96	91.81 232	96.80 178	89.66 163	93.90 208	95.44 220	92.80 108	98.72 153	92.74 93	98.52 171	98.32 130

test_fmvsmconf0.01_n		95.90 55	96.09 49	95.31 88	97.30 137	89.21 97	94.24 135	98.76 12	86.25 226	97.56 40	98.66 19	95.73 19	98.44 193	97.35 3	98.99 111	98.27 135

test_fmvsmconf0.1_n		95.61 66	95.72 71	95.26 89	96.85 159	89.20 98	93.51 160	98.60 15	85.68 239	97.42 50	98.30 37	95.34 33	98.39 194	96.85 4	98.98 112	98.19 141

test_fmvsmconf_n		95.43 74	95.50 78	95.22 93	96.48 186	89.19 99	93.23 170	98.36 23	85.61 242	96.92 72	98.02 50	95.23 39	98.38 197	96.69 7	98.95 121	98.09 149

test_8					96.37 189	89.14 100	90.51 263	96.89 171	79.37 318	90.42 297	94.36 261	91.20 144	98.82 132

ACMH+	88.43 11	96.48 31	96.82 16	95.47 80	98.54 46	89.06 101	95.65 82	98.61 14	96.10 30	98.16 25	97.52 80	96.90 7	98.62 171	90.30 156	99.60 25	98.72 94

MIMVSNet1		95.52 69	95.45 80	95.72 72	99.14 5	89.02 102	96.23 59	96.87 173	93.73 63	97.87 29	98.49 29	90.73 158	99.05 101	86.43 245	99.60 25	99.10 45

test_vis3_rt		90.40 228	90.03 239	91.52 239	92.58 326	88.95 103	90.38 268	97.72 104	73.30 360	97.79 31	97.51 83	77.05 308	87.10 398	89.03 195	94.89 322	98.50 120

UniMVSNet (Re)		95.32 81	95.15 94	95.80 69	97.79 105	88.91 104	92.91 179	98.07 64	93.46 70	96.31 96	95.97 195	90.14 168	99.34 63	92.11 105	99.64 23	99.16 36

agg_prior					96.20 208	88.89 105		96.88 172		90.21 302			98.78 144

SD-MVS		95.19 88	95.73 70	93.55 162	96.62 174	88.88 106	94.67 118	98.05 68	91.26 129	97.25 58	96.40 165	95.42 28	94.36 364	92.72 95	99.19 90	97.40 215
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
TSAR-MVS + MP.		94.96 95	94.75 108	95.57 77	98.86 22	88.69 107	96.37 46	96.81 177	85.23 248	94.75 181	97.12 116	91.85 126	99.40 47	93.45 67	98.33 189	98.62 113
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
plane_prior7					97.71 112	88.68 108

wuyk23d		87.83 289	90.79 222	78.96 384	90.46 372	88.63 109	92.72 184	90.67 332	91.65 120	98.68 13	97.64 70	96.06 15	77.53 406	59.84 400	99.41 54	70.73 404

test_fmvsm_n_1920		94.72 104	94.74 110	94.67 113	96.30 200	88.62 110	93.19 171	98.07 64	85.63 241	97.08 61	97.35 96	90.86 151	97.66 266	95.70 16	98.48 176	97.74 191

DP-MVS		95.62 65	95.84 65	94.97 100	97.16 144	88.62 110	94.54 128	97.64 107	96.94 18	96.58 87	97.32 100	93.07 100	98.72 153	90.45 148	98.84 131	97.57 201

UniMVSNet_NR-MVSNet		95.35 79	95.21 92	95.76 70	97.69 115	88.59 112	92.26 211	97.84 92	94.91 43	96.80 77	95.78 205	90.42 163	99.41 40	91.60 123	99.58 31	99.29 27

DU-MVS		95.28 85	95.12 96	95.75 71	97.75 107	88.59 112	92.58 191	97.81 95	93.99 56	96.80 77	95.90 196	90.10 171	99.41 40	91.60 123	99.58 31	99.26 28

nrg030		96.32 41	96.55 27	95.62 75	97.83 100	88.55 114	95.77 77	98.29 32	92.68 80	98.03 28	97.91 59	95.13 43	98.95 116	93.85 50	99.49 40	99.36 23

PS-MVSNAJss		96.01 51	96.04 54	95.89 66	98.82 25	88.51 115	95.57 88	97.88 88	88.72 183	98.81 8	98.86 10	90.77 154	99.60 11	95.43 24	99.53 37	99.57 13

tt0805		95.42 77	95.93 59	93.86 151	98.75 31	88.47 116	97.68 9	94.29 272	96.48 24	95.38 146	93.63 284	94.89 57	97.94 237	95.38 27	96.92 271	95.17 310

CDPH-MVS		92.67 178	91.83 198	95.18 95	96.94 152	88.46 117	90.70 257	97.07 157	77.38 333	92.34 264	95.08 234	92.67 111	98.88 123	85.74 252	98.57 166	98.20 140

plane_prior3						88.43 118			90.35 153	93.31 221

Fast-Effi-MVS+-dtu		92.77 175	92.16 187	94.58 122	94.66 287	88.25 119	92.05 216	96.65 188	89.62 164	90.08 304	91.23 334	92.56 112	98.60 174	86.30 247	96.27 289	96.90 239

plane_prior6					97.21 142	88.23 120						86.93 214

HQP_MVS		94.26 125	93.93 138	95.23 92	97.71 112	88.12 121	94.56 125	97.81 95	91.74 116	93.31 221	95.59 212	86.93 214	98.95 116	89.26 188	98.51 173	98.60 114

plane_prior						88.12 121	93.01 175		88.98 177						98.06 214

save fliter					97.46 130	88.05 123	92.04 217	97.08 156	87.63 209

UGNet		93.08 162	92.50 181	94.79 107	93.87 305	87.99 124	95.07 106	94.26 274	90.64 144	87.33 351	97.67 68	86.89 216	98.49 186	88.10 212	98.71 151	97.91 170
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
DeepC-MVS_fast	89.96 7	93.73 143	93.44 157	94.60 119	96.14 214	87.90 125	93.36 167	97.14 151	85.53 244	93.90 208	95.45 219	91.30 140	98.59 176	89.51 178	98.62 160	97.31 221
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CSCG		94.69 106	94.75 108	94.52 123	97.55 124	87.87 126	95.01 109	97.57 116	92.68 80	96.20 106	93.44 290	91.92 125	98.78 144	89.11 193	99.24 83	96.92 238

pmmvs-eth3d		91.54 205	90.73 224	93.99 141	95.76 243	87.86 127	90.83 252	93.98 281	78.23 330	94.02 203	96.22 183	82.62 262	96.83 310	86.57 240	98.33 189	97.29 222

pmmvs6		96.80 13	97.36 10	95.15 96	99.12 8	87.82 128	96.68 29	97.86 89	96.10 30	98.14 26	99.28 3	97.94 3	98.21 212	91.38 131	99.69 14	99.42 18

test_fmvsmvis_n_1920		95.08 91	95.40 84	94.13 138	96.66 169	87.75 129	93.44 164	98.49 17	85.57 243	98.27 22	97.11 117	94.11 76	97.75 259	96.26 11	98.72 149	96.89 240

TranMVSNet+NR-MVSNet		96.07 50	96.26 40	95.50 79	98.26 68	87.69 130	93.75 153	97.86 89	95.96 35	97.48 46	97.14 114	95.33 34	99.44 30	90.79 140	99.76 10	99.38 21

EC-MVSNet		95.44 73	95.62 74	94.89 102	96.93 154	87.69 130	96.48 40	99.14 5	93.93 59	92.77 245	94.52 256	93.95 78	99.49 26	93.62 57	99.22 87	97.51 206

alignmvs		93.26 156	92.85 170	94.50 124	95.70 245	87.45 132	93.45 163	95.76 226	91.58 121	95.25 158	92.42 316	81.96 269	98.72 153	91.61 122	97.87 229	97.33 220

UniMVSNet_ETH3D		97.13 6	97.72 4	95.35 83	99.51 2	87.38 133	97.70 8	97.54 118	98.16 3	98.94 4	99.33 2	97.84 4	99.08 96	90.73 142	99.73 13	99.59 12

新几何1				93.17 177	97.16 144	87.29 134		94.43 269	67.95 389	91.29 282	94.94 239	86.97 213	98.23 211	81.06 305	97.75 233	93.98 346

test_fmvs3		92.42 186	92.40 184	92.46 207	93.80 308	87.28 135	93.86 150	97.05 158	76.86 338	96.25 101	98.66 19	82.87 256	91.26 383	95.44 23	96.83 274	98.82 80

test_prior				94.61 116	95.95 229	87.23 136		97.36 134					98.68 164			97.93 168

MM		94.41 118	94.14 134	95.22 93	95.84 235	87.21 137	94.31 134	90.92 329	94.48 49	92.80 243	97.52 80	85.27 235	99.49 26	96.58 8	99.57 33	98.97 60

NR-MVSNet		95.28 85	95.28 90	95.26 89	97.75 107	87.21 137	95.08 105	97.37 129	93.92 61	97.65 35	95.90 196	90.10 171	99.33 68	90.11 165	99.66 21	99.26 28

test_one_0601					98.26 68	87.14 139		98.18 45	94.25 51	96.99 69	97.36 93	95.13 43

NP-MVS					96.82 162	87.10 140					93.40 291

3Dnovator	92.54 3	94.80 102	94.90 102	94.47 127	95.47 259	87.06 141	96.63 31	97.28 143	91.82 111	94.34 193	97.41 87	90.60 161	98.65 169	92.47 101	98.11 210	97.70 193

sasdasda		94.59 109	94.69 112	94.30 132	95.60 253	87.03 142	95.59 84	98.24 36	91.56 122	95.21 161	92.04 323	94.95 53	98.66 166	91.45 128	97.57 244	97.20 226

canonicalmvs		94.59 109	94.69 112	94.30 132	95.60 253	87.03 142	95.59 84	98.24 36	91.56 122	95.21 161	92.04 323	94.95 53	98.66 166	91.45 128	97.57 244	97.20 226

SED-MVS		96.00 52	96.41 34	94.76 108	98.51 49	86.97 144	95.21 99	98.10 58	91.95 99	97.63 36	97.25 103	96.48 10	99.35 60	93.29 75	99.29 73	97.95 166

test_241102_ONE					98.51 49	86.97 144		98.10 58	91.85 105	97.63 36	97.03 123	96.48 10	98.95 116

MVS_111021_HR		93.63 145	93.42 158	94.26 134	96.65 170	86.96 146	89.30 303	96.23 210	88.36 193	93.57 215	94.60 253	93.45 84	97.77 256	90.23 161	98.38 183	98.03 156

DP-MVS Recon		92.31 190	91.88 196	93.60 160	97.18 143	86.87 147	91.10 247	97.37 129	84.92 257	92.08 271	94.08 269	88.59 183	98.20 213	83.50 277	98.14 208	95.73 294

v7n		96.82 10	97.31 11	95.33 85	98.54 46	86.81 148	96.83 22	98.07 64	96.59 23	98.46 19	98.43 34	92.91 104	99.52 21	96.25 12	99.76 10	99.65 8

test_vis1_rt		85.58 320	84.58 323	88.60 316	87.97 392	86.76 149	85.45 369	93.59 284	66.43 392	87.64 346	89.20 361	79.33 286	85.38 402	81.59 298	89.98 386	93.66 354

test12				94.43 129	95.95 229	86.75 150		96.24 209		89.76 313		89.79 176	98.79 141		97.95 225	97.75 190

test_0728_SECOND				94.88 103	98.55 44	86.72 151	95.20 101	98.22 40					99.38 56	93.44 68	99.31 68	98.53 119

DVP-MVS		95.82 59	96.18 44	94.72 110	98.51 49	86.69 152	95.20 101	97.00 161	91.85 105	97.40 52	97.35 96	95.58 24	99.34 63	93.44 68	99.31 68	98.13 147
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					98.51 49	86.69 152	95.34 93	98.18 45	91.85 105	97.63 36	97.37 90	95.58 24

DVP-MVS++		95.93 53	96.34 36	94.70 111	96.54 179	86.66 154	98.45 4	98.22 40	93.26 74	97.54 41	97.36 93	93.12 97	99.38 56	93.88 48	98.68 155	98.04 153

IU-MVS					98.51 49	86.66 154		96.83 176	72.74 365	95.83 122				93.00 87	99.29 73	98.64 109

EG-PatchMatch MVS		94.54 113	94.67 116	94.14 137	97.87 99	86.50 156	92.00 219	96.74 183	88.16 197	96.93 71	97.61 72	93.04 101	97.90 238	91.60 123	98.12 209	98.03 156

MVP-Stereo		90.07 245	88.92 258	93.54 164	96.31 198	86.49 157	90.93 250	95.59 235	79.80 311	91.48 279	95.59 212	80.79 278	97.39 282	78.57 330	91.19 379	96.76 247
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CDS-MVSNet		89.55 253	88.22 277	93.53 165	95.37 264	86.49 157	89.26 304	93.59 284	79.76 313	91.15 286	92.31 317	77.12 307	98.38 197	77.51 337	97.92 227	95.71 295
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS-MVSNet		94.49 114	94.35 126	94.92 101	98.25 70	86.46 159	97.13 17	94.31 271	96.24 28	96.28 100	96.36 172	82.88 255	99.35 60	88.19 209	99.52 39	98.96 62

WR-MVS_H		96.60 26	97.05 14	95.24 91	99.02 12	86.44 160	96.78 26	98.08 61	97.42 10	98.48 18	97.86 62	91.76 131	99.63 9	94.23 42	99.84 3	99.66 6

PMMVS		83.00 341	81.11 350	88.66 315	83.81 409	86.44 160	82.24 389	85.65 368	61.75 402	82.07 388	85.64 387	79.75 283	91.59 382	75.99 350	93.09 362	87.94 392

TAMVS		90.16 239	89.05 254	93.49 169	96.49 184	86.37 162	90.34 270	92.55 307	80.84 307	92.99 237	94.57 255	81.94 270	98.20 213	73.51 363	98.21 202	95.90 288

AdaColmap		91.63 203	91.36 209	92.47 206	95.56 255	86.36 163	92.24 213	96.27 207	88.88 181	89.90 309	92.69 308	91.65 132	98.32 203	77.38 339	97.64 241	92.72 369

Anonymous20231211		96.60 26	97.13 13	95.00 99	97.46 130	86.35 164	97.11 18	98.24 36	97.58 9	98.72 10	98.97 7	93.15 96	99.15 87	93.18 80	99.74 12	99.50 16

ETV-MVS		92.99 165	92.74 173	93.72 157	95.86 233	86.30 165	92.33 205	97.84 92	91.70 119	92.81 242	86.17 383	92.22 118	99.19 84	88.03 216	97.73 234	95.66 299

fmvsm_l_conf0.5_n		93.79 141	93.81 140	93.73 156	96.16 211	86.26 166	92.46 197	96.72 184	81.69 298	95.77 124	97.11 117	90.83 153	97.82 249	95.58 19	97.99 221	97.11 229

API-MVS		91.52 206	91.61 201	91.26 250	94.16 296	86.26 166	94.66 119	94.82 260	91.17 132	92.13 270	91.08 337	90.03 174	97.06 299	79.09 327	97.35 255	90.45 385

EPNet		89.80 252	88.25 274	94.45 128	83.91 408	86.18 168	93.87 149	87.07 357	91.16 133	80.64 396	94.72 248	78.83 289	98.89 122	85.17 257	98.89 124	98.28 134
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
JIA-IIPM		85.08 324	83.04 336	91.19 255	87.56 394	86.14 169	89.40 300	84.44 381	88.98 177	82.20 387	97.95 54	56.82 390	96.15 329	76.55 346	83.45 398	91.30 380

test_f		86.65 314	87.13 297	85.19 359	90.28 374	86.11 170	86.52 356	91.66 322	69.76 383	95.73 130	97.21 109	69.51 343	81.28 405	89.15 192	94.40 333	88.17 391

VDD-MVS		94.37 119	94.37 124	94.40 130	97.49 127	86.07 171	93.97 147	93.28 291	94.49 48	96.24 102	97.78 63	87.99 194	98.79 141	88.92 197	99.14 97	98.34 129

MVS_0304		92.88 169	92.27 185	94.69 112	92.35 332	86.03 172	92.88 181	89.68 336	90.53 147	91.52 278	96.43 162	82.52 263	99.32 69	95.01 30	99.54 36	98.71 97

EI-MVSNet-Vis-set		94.36 120	94.28 128	94.61 116	92.55 328	85.98 173	92.44 199	94.69 265	93.70 64	96.12 110	95.81 201	91.24 141	98.86 127	93.76 55	98.22 201	98.98 58

mvsany_test1		83.91 334	82.93 338	86.84 343	86.18 402	85.93 174	81.11 392	75.03 407	70.80 378	88.57 333	94.63 251	83.08 253	87.38 397	80.39 307	86.57 393	87.21 393

Anonymous20240529		95.50 71	95.83 66	94.50 124	97.33 136	85.93 174	95.19 103	96.77 181	96.64 22	97.61 39	98.05 46	93.23 93	98.79 141	88.60 205	99.04 109	98.78 85

EI-MVSNet-UG-set		94.35 121	94.27 130	94.59 120	92.46 331	85.87 176	92.42 201	94.69 265	93.67 67	96.13 109	95.84 200	91.20 144	98.86 127	93.78 52	98.23 199	99.03 50

PCF-MVS	84.52 17	89.12 262	87.71 285	93.34 172	96.06 220	85.84 177	86.58 355	97.31 138	68.46 388	93.61 214	93.89 278	87.51 201	98.52 184	67.85 388	98.11 210	95.66 299
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_0402		95.73 62	96.22 42	94.26 134	98.19 74	85.77 178	93.24 169	97.24 145	96.88 19	97.69 34	97.77 65	94.12 75	99.13 91	91.54 127	99.29 73	97.88 174

fmvsm_s_conf0.5_n_a		94.02 135	94.08 137	93.84 152	96.72 166	85.73 179	93.65 158	95.23 249	83.30 274	95.13 163	97.56 75	92.22 118	97.17 292	95.51 21	97.41 252	98.64 109

fmvsm_s_conf0.1_n_a		94.26 125	94.37 124	93.95 146	97.36 134	85.72 180	94.15 139	95.44 241	83.25 276	95.51 138	98.05 46	92.54 113	97.19 291	95.55 20	97.46 250	98.94 64

MCST-MVS		92.91 167	92.51 180	94.10 139	97.52 125	85.72 180	91.36 242	97.13 153	80.33 309	92.91 241	94.24 263	91.23 142	98.72 153	89.99 169	97.93 226	97.86 176

fmvsm_l_conf0.5_n_a		93.59 146	93.63 149	93.49 169	96.10 217	85.66 182	92.32 206	96.57 193	81.32 301	95.63 133	97.14 114	90.19 167	97.73 262	95.37 28	98.03 217	97.07 230

pmmvs4		88.95 270	87.70 286	92.70 192	94.30 294	85.60 183	87.22 337	92.16 314	74.62 352	89.75 314	94.19 265	77.97 298	96.41 322	82.71 284	96.36 287	96.09 277

EPP-MVSNet		93.91 139	93.68 148	94.59 120	98.08 80	85.55 184	97.44 11	94.03 277	94.22 53	94.94 173	96.19 184	82.07 267	99.57 16	87.28 229	98.89 124	98.65 104

MGCFI-Net		94.44 116	94.67 116	93.75 155	95.56 255	85.47 185	95.25 98	98.24 36	91.53 124	95.04 169	92.21 318	94.94 55	98.54 182	91.56 126	97.66 240	97.24 224

test_fmvs2		90.62 223	90.40 232	91.29 248	91.93 348	85.46 186	92.70 186	96.48 200	74.44 353	94.91 175	97.59 73	75.52 320	90.57 385	93.44 68	96.56 282	97.84 179

CMPMVS	68.83 22	87.28 303	85.67 317	92.09 218	88.77 389	85.42 187	90.31 271	94.38 270	70.02 382	88.00 340	93.30 293	73.78 327	94.03 368	75.96 351	96.54 283	96.83 243
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ACMH	88.36 12	96.59 28	97.43 6	94.07 140	98.56 41	85.33 188	96.33 49	98.30 29	94.66 45	98.72 10	98.30 37	97.51 5	98.00 231	94.87 31	99.59 27	98.86 76
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test222					96.95 151	85.27 189	88.83 314	93.61 283	65.09 397	90.74 292	94.85 242	84.62 242			97.36 254	93.91 347

GeoE		94.55 112	94.68 115	94.15 136	97.23 139	85.11 190	94.14 141	97.34 136	88.71 184	95.26 156	95.50 217	94.65 63	99.12 92	90.94 138	98.40 179	98.23 137

pm-mvs1		95.43 74	95.94 57	93.93 147	98.38 60	85.08 191	95.46 91	97.12 154	91.84 108	97.28 56	98.46 32	95.30 36	97.71 263	90.17 163	99.42 50	98.99 54

HQP5-MVS						84.89 192

HQP-MVS		92.09 195	91.49 206	93.88 149	96.36 191	84.89 192	91.37 239	97.31 138	87.16 215	88.81 324	93.40 291	84.76 240	98.60 174	86.55 242	97.73 234	98.14 146

DTE-MVSNet		96.74 18	97.43 6	94.67 113	99.13 6	84.68 194	96.51 37	97.94 87	98.14 4	98.67 14	98.32 36	95.04 48	99.69 5	93.27 77	99.82 7	99.62 10

PEN-MVS		96.69 21	97.39 9	94.61 116	99.16 4	84.50 195	96.54 34	98.05 68	98.06 5	98.64 15	98.25 39	95.01 51	99.65 6	92.95 89	99.83 5	99.68 4

fmvsm_s_conf0.1_n		94.19 131	94.41 121	93.52 167	97.22 141	84.37 196	93.73 154	95.26 248	84.45 263	95.76 125	98.00 51	91.85 126	97.21 288	95.62 17	97.82 231	98.98 58

fmvsm_s_conf0.5_n		94.00 136	94.20 132	93.42 171	96.69 167	84.37 196	93.38 166	95.13 251	84.50 262	95.40 145	97.55 79	91.77 129	97.20 289	95.59 18	97.79 232	98.69 101

GBi-Net		93.21 159	92.96 165	93.97 143	95.40 261	84.29 198	95.99 67	96.56 194	88.63 185	95.10 165	98.53 26	81.31 274	98.98 109	86.74 235	98.38 183	98.65 104

test1		93.21 159	92.96 165	93.97 143	95.40 261	84.29 198	95.99 67	96.56 194	88.63 185	95.10 165	98.53 26	81.31 274	98.98 109	86.74 235	98.38 183	98.65 104

FMVSNet1		94.84 99	95.13 95	93.97 143	97.60 120	84.29 198	95.99 67	96.56 194	92.38 86	97.03 66	98.53 26	90.12 169	98.98 109	88.78 201	99.16 95	98.65 104

原ACMM1				92.87 187	96.91 155	84.22 201		97.01 160	76.84 339	89.64 315	94.46 257	88.00 193	98.70 160	81.53 299	98.01 220	95.70 297

DPM-MVS		89.35 258	88.40 267	92.18 215	96.13 216	84.20 202	86.96 342	96.15 216	75.40 347	87.36 350	91.55 332	83.30 250	98.01 230	82.17 293	96.62 281	94.32 339

旧先验1					96.20 208	84.17 203		94.82 260			95.57 216	89.57 177			97.89 228	96.32 264

OpenMVS	89.45 8	92.27 192	92.13 190	92.68 194	94.53 290	84.10 204	95.70 79	97.03 159	82.44 290	91.14 287	96.42 163	88.47 185	98.38 197	85.95 250	97.47 249	95.55 304

PS-CasMVS		96.69 21	97.43 6	94.49 126	99.13 6	84.09 205	96.61 32	97.97 81	97.91 6	98.64 15	98.13 42	95.24 38	99.65 6	93.39 72	99.84 3	99.72 2

EIA-MVS		92.35 189	92.03 191	93.30 174	95.81 239	83.97 206	92.80 183	98.17 49	87.71 206	89.79 312	87.56 373	91.17 147	99.18 85	87.97 217	97.27 256	96.77 246

PVSNet_Blended_VisFu		91.63 203	91.20 212	92.94 184	97.73 110	83.95 207	92.14 214	97.46 125	78.85 327	92.35 262	94.98 237	84.16 245	99.08 96	86.36 246	96.77 277	95.79 292

CP-MVSNet		96.19 46	96.80 17	94.38 131	98.99 16	83.82 208	96.31 52	97.53 120	97.60 8	98.34 21	97.52 80	91.98 124	99.63 9	93.08 85	99.81 8	99.70 3

lessismore_v0				93.87 150	98.05 83	83.77 209		80.32 397		97.13 60	97.91 59	77.49 301	99.11 94	92.62 97	98.08 213	98.74 92

CLD-MVS		91.82 198	91.41 208	93.04 178	96.37 189	83.65 210	86.82 347	97.29 141	84.65 261	92.27 266	89.67 355	92.20 120	97.85 248	83.95 275	99.47 41	97.62 198
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CANet		92.38 188	91.99 193	93.52 167	93.82 307	83.46 211	91.14 245	97.00 161	89.81 160	86.47 355	94.04 270	87.90 196	99.21 80	89.50 179	98.27 194	97.90 171

QAPM		92.88 169	92.77 171	93.22 176	95.82 237	83.31 212	96.45 41	97.35 135	83.91 268	93.75 210	96.77 139	89.25 180	98.88 123	84.56 270	97.02 265	97.49 207

Effi-MVS+		92.79 173	92.74 173	92.94 184	95.10 269	83.30 213	94.00 145	97.53 120	91.36 128	89.35 318	90.65 346	94.01 77	98.66 166	87.40 227	95.30 312	96.88 242

sd_testset		93.94 138	94.39 122	92.61 200	97.93 94	83.24 214	93.17 172	95.04 253	93.65 68	95.51 138	98.63 21	94.49 69	95.89 337	81.72 297	99.35 60	98.70 98

casdiffmvs_mvg		95.10 90	95.62 74	93.53 165	96.25 205	83.23 215	92.66 188	98.19 43	93.06 77	97.49 45	97.15 113	94.78 59	98.71 159	92.27 104	98.72 149	98.65 104
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Anonymous202405211		92.58 181	92.50 181	92.83 189	96.55 178	83.22 216	92.43 200	91.64 323	94.10 55	95.59 135	96.64 152	81.88 271	97.50 273	85.12 261	98.52 171	97.77 187

SixPastTwentyTwo		94.91 96	95.21 92	93.98 142	98.52 48	83.19 217	95.93 71	94.84 259	94.86 44	98.49 17	98.74 16	81.45 272	99.60 11	94.69 33	99.39 56	99.15 37

VPA-MVSNet		95.14 89	95.67 73	93.58 161	97.76 106	83.15 218	94.58 123	97.58 115	93.39 71	97.05 65	98.04 48	93.25 92	98.51 185	89.75 175	99.59 27	99.08 46

LCM-MVSNet-Re		94.20 129	94.58 119	93.04 178	95.91 231	83.13 219	93.79 152	99.19 4	92.00 98	98.84 7	98.04 48	93.64 80	99.02 106	81.28 301	98.54 169	96.96 237

MSDG		90.82 215	90.67 225	91.26 250	94.16 296	83.08 220	86.63 352	96.19 213	90.60 146	91.94 273	91.89 325	89.16 181	95.75 339	80.96 306	94.51 332	94.95 320

ambc				92.98 180	96.88 156	83.01 221	95.92 72	96.38 204		96.41 91	97.48 85	88.26 187	97.80 251	89.96 170	98.93 122	98.12 148

dmvs_re		84.69 328	83.94 330	86.95 340	92.24 335	82.93 222	89.51 295	87.37 354	84.38 265	85.37 360	85.08 390	72.44 330	86.59 399	68.05 387	91.03 382	91.33 379

SDMVSNet		94.43 117	95.02 99	92.69 193	97.93 94	82.88 223	91.92 224	95.99 222	93.65 68	95.51 138	98.63 21	94.60 65	96.48 319	87.57 223	99.35 60	98.70 98

MSLP-MVS++		93.25 158	93.88 139	91.37 243	96.34 195	82.81 224	93.11 173	97.74 102	89.37 169	94.08 198	95.29 227	90.40 165	96.35 326	90.35 153	98.25 197	94.96 319

K. test v3		93.37 152	93.27 162	93.66 158	98.05 83	82.62 225	94.35 131	86.62 359	96.05 32	97.51 44	98.85 12	76.59 316	99.65 6	93.21 79	98.20 204	98.73 93

test_fmvs1_n		88.73 276	88.38 268	89.76 294	92.06 343	82.53 226	92.30 209	96.59 192	71.14 373	92.58 251	95.41 224	68.55 345	89.57 393	91.12 133	95.66 301	97.18 228

Fast-Effi-MVS+		91.28 212	90.86 219	92.53 204	95.45 260	82.53 226	89.25 306	96.52 198	85.00 255	89.91 308	88.55 367	92.94 102	98.84 130	84.72 269	95.44 307	96.22 272

test_vis1_n		89.01 267	89.01 256	89.03 307	92.57 327	82.46 228	92.62 190	96.06 217	73.02 363	90.40 298	95.77 206	74.86 322	89.68 391	90.78 141	94.98 320	94.95 320

VDDNet		94.03 134	94.27 130	93.31 173	98.87 21	82.36 229	95.51 90	91.78 321	97.19 13	96.32 95	98.60 23	84.24 244	98.75 148	87.09 232	98.83 136	98.81 82

mvsmamba		90.24 237	89.43 250	92.64 195	95.52 257	82.36 229	96.64 30	92.29 310	81.77 296	92.14 269	96.28 178	70.59 339	99.10 95	84.44 272	95.22 315	96.47 258

114514_t		90.51 224	89.80 244	92.63 198	98.00 89	82.24 231	93.40 165	97.29 141	65.84 395	89.40 317	94.80 245	86.99 212	98.75 148	83.88 276	98.61 161	96.89 240

testdata				91.03 258	96.87 157	82.01 232		94.28 273	71.55 370	92.46 255	95.42 221	85.65 231	97.38 284	82.64 285	97.27 256	93.70 353

FMVSNet2		92.78 174	92.73 175	92.95 183	95.40 261	81.98 233	94.18 138	95.53 239	88.63 185	96.05 112	97.37 90	81.31 274	98.81 137	87.38 228	98.67 157	98.06 150

TransMVSNet (Re)		95.27 87	96.04 54	92.97 181	98.37 62	81.92 234	95.07 106	96.76 182	93.97 58	97.77 32	98.57 24	95.72 20	97.90 238	88.89 199	99.23 84	99.08 46

FC-MVSNet-test		95.32 81	95.88 62	93.62 159	98.49 56	81.77 235	95.90 73	98.32 26	93.93 59	97.53 43	97.56 75	88.48 184	99.40 47	92.91 90	99.83 5	99.68 4

FIs		94.90 97	95.35 85	93.55 162	98.28 66	81.76 236	95.33 94	98.14 53	93.05 78	97.07 62	97.18 111	87.65 198	99.29 71	91.72 119	99.69 14	99.61 11

ab-mvs		92.40 187	92.62 178	91.74 228	97.02 148	81.65 237	95.84 75	95.50 240	86.95 220	92.95 240	97.56 75	90.70 159	97.50 273	79.63 320	97.43 251	96.06 279

xiu_mvs_v1_base_debu		91.47 207	91.52 203	91.33 245	95.69 246	81.56 238	89.92 283	96.05 219	83.22 277	91.26 283	90.74 341	91.55 134	98.82 132	89.29 185	95.91 295	93.62 356

xiu_mvs_v1_base		91.47 207	91.52 203	91.33 245	95.69 246	81.56 238	89.92 283	96.05 219	83.22 277	91.26 283	90.74 341	91.55 134	98.82 132	89.29 185	95.91 295	93.62 356

xiu_mvs_v1_base_debi		91.47 207	91.52 203	91.33 245	95.69 246	81.56 238	89.92 283	96.05 219	83.22 277	91.26 283	90.74 341	91.55 134	98.82 132	89.29 185	95.91 295	93.62 356

casdiffmvs		94.32 123	94.80 106	92.85 188	96.05 221	81.44 241	92.35 204	98.05 68	91.53 124	95.75 127	96.80 138	93.35 89	98.49 186	91.01 137	98.32 191	98.64 109
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ET-MVSNet_ETH3D		86.15 316	84.27 327	91.79 226	93.04 319	81.28 242	87.17 339	86.14 362	79.57 316	83.65 376	88.66 364	57.10 388	98.18 216	87.74 221	95.40 308	95.90 288

test_fmvs1		87.59 296	87.27 292	88.54 317	88.32 391	81.26 243	90.43 267	95.72 228	70.55 379	91.70 276	94.63 251	68.13 346	89.42 394	90.59 145	95.34 311	94.94 322

V42		93.43 151	93.58 152	92.97 181	95.34 265	81.22 244	92.67 187	96.49 199	87.25 214	96.20 106	96.37 171	87.32 204	98.85 129	92.39 103	98.21 202	98.85 79

OpenMVS_ROB	85.12 16	89.52 255	89.05 254	90.92 263	94.58 289	81.21 245	91.10 247	93.41 290	77.03 337	93.41 218	93.99 274	83.23 251	97.80 251	79.93 317	94.80 326	93.74 352

PAPM_NR		91.03 214	90.81 221	91.68 232	96.73 165	81.10 246	93.72 155	96.35 205	88.19 195	88.77 328	92.12 322	85.09 238	97.25 286	82.40 290	93.90 347	96.68 249

baseline		94.26 125	94.80 106	92.64 195	96.08 219	80.99 247	93.69 156	98.04 72	90.80 140	94.89 176	96.32 174	93.19 94	98.48 190	91.68 121	98.51 173	98.43 126

1112_ss		88.42 280	87.41 289	91.45 241	96.69 167	80.99 247	89.72 290	96.72 184	73.37 359	87.00 353	90.69 344	77.38 304	98.20 213	81.38 300	93.72 350	95.15 312

tfpnnormal		94.27 124	94.87 104	92.48 205	97.71 112	80.88 249	94.55 127	95.41 244	93.70 64	96.67 83	97.72 66	91.40 137	98.18 216	87.45 225	99.18 92	98.36 128

Baseline_NR-MVSNet		94.47 115	95.09 98	92.60 201	98.50 55	80.82 250	92.08 215	96.68 186	93.82 62	96.29 98	98.56 25	90.10 171	97.75 259	90.10 167	99.66 21	99.24 30

HyFIR lowres test		87.19 307	85.51 318	92.24 210	97.12 147	80.51 251	85.03 372	96.06 217	66.11 394	91.66 277	92.98 301	70.12 341	99.14 89	75.29 353	95.23 314	97.07 230

UnsupCasMVSNet_eth		90.33 234	90.34 233	90.28 281	94.64 288	80.24 252	89.69 291	95.88 223	85.77 236	93.94 207	95.69 209	81.99 268	92.98 376	84.21 273	91.30 378	97.62 198

MDA-MVSNet-bldmvs		91.04 213	90.88 218	91.55 237	94.68 286	80.16 253	85.49 368	92.14 315	90.41 152	94.93 174	95.79 202	85.10 237	96.93 305	85.15 259	94.19 342	97.57 201

v10		94.68 107	95.27 91	92.90 186	96.57 176	80.15 254	94.65 120	97.57 116	90.68 143	97.43 48	98.00 51	88.18 188	99.15 87	94.84 32	99.55 35	99.41 19

VNet		92.67 178	92.96 165	91.79 226	96.27 202	80.15 254	91.95 220	94.98 255	92.19 95	94.52 188	96.07 190	87.43 202	97.39 282	84.83 266	98.38 183	97.83 180

DELS-MVS		92.05 196	92.16 187	91.72 229	94.44 291	80.13 256	87.62 328	97.25 144	87.34 213	92.22 267	93.18 297	89.54 178	98.73 152	89.67 176	98.20 204	96.30 265
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
jason		89.17 261	88.32 269	91.70 231	95.73 244	80.07 257	88.10 324	93.22 292	71.98 368	90.09 303	92.79 305	78.53 294	98.56 179	87.43 226	97.06 263	96.46 259
jason: jason.
MVSFormer		92.18 194	92.23 186	92.04 220	94.74 282	80.06 258	97.15 15	97.37 129	88.98 177	88.83 322	92.79 305	77.02 309	99.60 11	96.41 9	96.75 278	96.46 259

lupinMVS		88.34 282	87.31 290	91.45 241	94.74 282	80.06 258	87.23 336	92.27 311	71.10 374	88.83 322	91.15 335	77.02 309	98.53 183	86.67 238	96.75 278	95.76 293

WR-MVS		93.49 148	93.72 145	92.80 190	97.57 123	80.03 260	90.14 276	95.68 229	93.70 64	96.62 85	95.39 225	87.21 206	99.04 104	87.50 224	99.64 23	99.33 24

CANet_DTU		89.85 250	89.17 252	91.87 223	92.20 338	80.02 261	90.79 253	95.87 224	86.02 232	82.53 386	91.77 327	80.01 282	98.57 178	85.66 254	97.70 237	97.01 235

FA-MVS(test-final)		91.81 199	91.85 197	91.68 232	94.95 272	79.99 262	96.00 66	93.44 289	87.80 203	94.02 203	97.29 101	77.60 300	98.45 192	88.04 215	97.49 247	96.61 250

Patchmatch-RL test		88.81 273	88.52 264	89.69 297	95.33 266	79.94 263	86.22 360	92.71 302	78.46 328	95.80 123	94.18 266	66.25 359	95.33 350	89.22 190	98.53 170	93.78 350

FMVSNet3		90.78 217	90.32 234	92.16 216	93.03 320	79.92 264	92.54 192	94.95 256	86.17 230	95.10 165	96.01 193	69.97 342	98.75 148	86.74 235	98.38 183	97.82 182

XXY-MVS		92.58 181	93.16 164	90.84 267	97.75 107	79.84 265	91.87 228	96.22 212	85.94 233	95.53 137	97.68 67	92.69 110	94.48 360	83.21 280	97.51 246	98.21 139

test_yl		90.11 242	89.73 247	91.26 250	94.09 299	79.82 266	90.44 264	92.65 303	90.90 135	93.19 231	93.30 293	73.90 325	98.03 226	82.23 291	96.87 272	95.93 285

DCV-MVSNet		90.11 242	89.73 247	91.26 250	94.09 299	79.82 266	90.44 264	92.65 303	90.90 135	93.19 231	93.30 293	73.90 325	98.03 226	82.23 291	96.87 272	95.93 285

FMVSNet5		87.82 290	86.56 307	91.62 234	92.31 333	79.81 268	93.49 161	94.81 262	83.26 275	91.36 281	96.93 130	52.77 397	97.49 275	76.07 349	98.03 217	97.55 204

v8		94.65 108	95.29 89	92.74 191	96.65 170	79.77 269	94.59 121	97.17 149	91.86 104	97.47 47	97.93 55	88.16 189	99.08 96	94.32 39	99.47 41	99.38 21

tttt0517		89.81 251	88.90 260	92.55 203	97.00 149	79.73 270	95.03 108	83.65 383	89.88 159	95.30 152	94.79 246	53.64 395	99.39 50	91.99 110	98.79 143	98.54 117

v1192		93.49 148	93.78 143	92.62 199	96.16 211	79.62 271	91.83 231	97.22 147	86.07 231	96.10 111	96.38 170	87.22 205	99.02 106	94.14 44	98.88 126	99.22 31

v1144		93.50 147	93.81 140	92.57 202	96.28 201	79.61 272	91.86 230	96.96 164	86.95 220	95.91 118	96.32 174	87.65 198	98.96 114	93.51 61	98.88 126	99.13 39

FE-MVS		89.06 264	88.29 271	91.36 244	94.78 279	79.57 273	96.77 27	90.99 327	84.87 258	92.96 239	96.29 176	60.69 384	98.80 140	80.18 312	97.11 262	95.71 295

BH-untuned		90.68 220	90.90 217	90.05 290	95.98 227	79.57 273	90.04 279	94.94 257	87.91 199	94.07 199	93.00 299	87.76 197	97.78 255	79.19 326	95.17 316	92.80 368

KD-MVS_self_test		94.10 132	94.73 111	92.19 212	97.66 118	79.49 275	94.86 113	97.12 154	89.59 165	96.87 73	97.65 69	90.40 165	98.34 202	89.08 194	99.35 60	98.75 89

CHOSEN 1792x2688		87.19 307	85.92 316	91.00 261	97.13 146	79.41 276	84.51 378	95.60 231	64.14 398	90.07 305	94.81 243	78.26 296	97.14 295	73.34 364	95.38 310	96.46 259

thisisatest0530		88.69 277	87.52 288	92.20 211	96.33 196	79.36 277	92.81 182	84.01 382	86.44 223	93.67 213	92.68 309	53.62 396	99.25 77	89.65 177	98.45 177	98.00 158

LFMVS		91.33 210	91.16 215	91.82 225	96.27 202	79.36 277	95.01 109	85.61 370	96.04 33	94.82 178	97.06 121	72.03 334	98.46 191	84.96 265	98.70 153	97.65 197

TR-MVS		87.70 291	87.17 295	89.27 304	94.11 298	79.26 279	88.69 318	91.86 320	81.94 295	90.69 293	89.79 352	82.82 258	97.42 279	72.65 369	91.98 375	91.14 381

test20.03		90.80 216	90.85 220	90.63 273	95.63 251	79.24 280	89.81 287	92.87 297	89.90 158	94.39 190	96.40 165	85.77 228	95.27 352	73.86 362	99.05 104	97.39 216

IterMVS-SCA-FT		91.65 202	91.55 202	91.94 221	93.89 304	79.22 281	87.56 331	93.51 287	91.53 124	95.37 148	96.62 153	78.65 291	98.90 120	91.89 114	94.95 321	97.70 193

EI-MVSNet		92.99 165	93.26 163	92.19 212	92.12 341	79.21 282	92.32 206	94.67 267	91.77 114	95.24 159	95.85 198	87.14 208	98.49 186	91.99 110	98.26 195	98.86 76

IterMVS-LS		93.78 142	94.28 128	92.27 209	96.27 202	79.21 282	91.87 228	96.78 179	91.77 114	96.57 88	97.07 120	87.15 207	98.74 151	91.99 110	99.03 110	98.86 76
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CR-MVSNet		87.89 287	87.12 298	90.22 284	91.01 364	78.93 284	92.52 193	92.81 298	73.08 362	89.10 319	96.93 130	67.11 351	97.64 268	88.80 200	92.70 367	94.08 341

RPMNet		90.31 236	90.14 238	90.81 269	91.01 364	78.93 284	92.52 193	98.12 55	91.91 102	89.10 319	96.89 133	68.84 344	99.41 40	90.17 163	92.70 367	94.08 341

test_cas_vis1_n_1920		88.25 283	88.27 273	88.20 325	92.19 339	78.92 286	89.45 297	95.44 241	75.29 350	93.23 229	95.65 211	71.58 335	90.23 389	88.05 214	93.55 354	95.44 306

patch_mono-2		92.46 185	92.72 176	91.71 230	96.65 170	78.91 287	88.85 313	97.17 149	83.89 269	92.45 256	96.76 141	89.86 175	97.09 296	90.24 160	98.59 164	99.12 41

MVSMamba_PlusPlus		94.82 101	95.89 61	91.62 234	97.82 101	78.88 288	96.52 35	97.60 113	97.14 14	94.23 194	98.48 30	87.01 210	99.71 3	95.43 24	98.80 140	96.28 267

bld_raw_conf03		92.59 180	92.96 165	91.47 240	95.85 234	78.88 288	96.52 35	97.60 113	83.31 273	94.23 194	96.75 143	84.27 243	99.26 76	89.30 183	98.80 140	96.28 267

UnsupCasMVSNet_bld		88.50 279	88.03 281	89.90 292	95.52 257	78.88 288	87.39 335	94.02 279	79.32 321	93.06 234	94.02 272	80.72 279	94.27 365	75.16 354	93.08 363	96.54 251

v2v482		93.29 154	93.63 149	92.29 208	96.35 194	78.82 291	91.77 234	96.28 206	88.45 190	95.70 132	96.26 181	86.02 227	98.90 120	93.02 86	98.81 139	99.14 38

Anonymous20231206		88.77 274	88.29 271	90.20 286	96.31 198	78.81 292	89.56 294	93.49 288	74.26 355	92.38 260	95.58 215	82.21 264	95.43 347	72.07 371	98.75 148	96.34 263

PVSNet_BlendedMVS		90.35 233	89.96 240	91.54 238	94.81 277	78.80 293	90.14 276	96.93 166	79.43 317	88.68 331	95.06 235	86.27 224	98.15 219	80.27 309	98.04 216	97.68 195

PVSNet_Blended		88.74 275	88.16 280	90.46 278	94.81 277	78.80 293	86.64 351	96.93 166	74.67 351	88.68 331	89.18 362	86.27 224	98.15 219	80.27 309	96.00 293	94.44 336

BH-RMVSNet		90.47 226	90.44 230	90.56 275	95.21 268	78.65 295	89.15 307	93.94 282	88.21 194	92.74 246	94.22 264	86.38 222	97.88 242	78.67 329	95.39 309	95.14 313

balanced_conf03		93.45 150	94.17 133	91.28 249	95.81 239	78.40 296	96.20 60	97.48 124	88.56 189	95.29 154	97.20 110	85.56 234	99.21 80	92.52 100	98.91 123	96.24 271

D2MVS		89.93 248	89.60 249	90.92 263	94.03 301	78.40 296	88.69 318	94.85 258	78.96 325	93.08 233	95.09 233	74.57 323	96.94 303	88.19 209	98.96 119	97.41 212

v1921920		93.26 156	93.61 151	92.19 212	96.04 225	78.31 298	91.88 227	97.24 145	85.17 250	96.19 108	96.19 184	86.76 218	99.05 101	94.18 43	98.84 131	99.22 31

v144192		93.20 161	93.54 155	92.16 216	96.05 221	78.26 299	91.95 220	97.14 151	84.98 256	95.96 114	96.11 188	87.08 209	99.04 104	93.79 51	98.84 131	99.17 35

diffmvs		91.74 200	91.93 195	91.15 256	93.06 318	78.17 300	88.77 316	97.51 123	86.28 225	92.42 258	93.96 275	88.04 192	97.46 276	90.69 144	96.67 280	97.82 182
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
sss		87.23 304	86.82 302	88.46 321	93.96 302	77.94 301	86.84 345	92.78 301	77.59 332	87.61 348	91.83 326	78.75 290	91.92 380	77.84 333	94.20 340	95.52 305

MS-PatchMatch		88.05 286	87.75 284	88.95 308	93.28 313	77.93 302	87.88 327	92.49 308	75.42 346	92.57 252	93.59 287	80.44 280	94.24 367	81.28 301	92.75 366	94.69 332

HY-MVS	82.50 18	86.81 313	85.93 315	89.47 298	93.63 309	77.93 302	94.02 144	91.58 324	75.68 343	83.64 377	93.64 283	77.40 303	97.42 279	71.70 374	92.07 374	93.05 365

v1240		93.29 154	93.71 146	92.06 219	96.01 226	77.89 304	91.81 232	97.37 129	85.12 252	96.69 82	96.40 165	86.67 219	99.07 100	94.51 35	98.76 146	99.22 31

CL-MVSNet_self_test		90.04 247	89.90 242	90.47 276	95.24 267	77.81 305	86.60 354	92.62 305	85.64 240	93.25 228	93.92 276	83.84 246	96.06 333	79.93 317	98.03 217	97.53 205

Test_1112_low_res		87.50 299	86.58 306	90.25 283	96.80 164	77.75 306	87.53 333	96.25 208	69.73 384	86.47 355	93.61 286	75.67 319	97.88 242	79.95 315	93.20 359	95.11 316

v148		92.87 171	93.29 159	91.62 234	96.25 205	77.72 307	91.28 243	95.05 252	89.69 162	95.93 117	96.04 191	87.34 203	98.38 197	90.05 168	97.99 221	98.78 85

MVS		84.98 325	84.30 326	87.01 338	91.03 363	77.69 308	91.94 222	94.16 275	59.36 403	84.23 373	87.50 375	85.66 230	96.80 311	71.79 372	93.05 364	86.54 395

iter_conf05		95.52 69	96.74 19	91.88 222	97.82 101	77.68 309	97.26 13	98.91 8	97.14 14	99.22 3	98.48 30	87.01 210	99.71 3	95.43 24	99.38 57	98.25 136

miper_lstm_enhance		89.90 249	89.80 244	90.19 287	91.37 360	77.50 310	83.82 384	95.00 254	84.84 259	93.05 235	94.96 238	76.53 317	95.20 353	89.96 170	98.67 157	97.86 176

pmmvs3		80.83 359	78.96 367	86.45 347	87.23 397	77.48 311	84.87 373	82.31 387	63.83 399	85.03 365	89.50 357	49.66 398	93.10 374	73.12 367	95.10 317	88.78 390

PAPR		87.65 294	86.77 304	90.27 282	92.85 324	77.38 312	88.56 321	96.23 210	76.82 340	84.98 366	89.75 354	86.08 226	97.16 294	72.33 370	93.35 356	96.26 270

Vis-MVSNet (Re-imp)		90.42 227	90.16 235	91.20 254	97.66 118	77.32 313	94.33 132	87.66 352	91.20 131	92.99 237	95.13 231	75.40 321	98.28 205	77.86 332	99.19 90	97.99 161

BH-w/o		87.21 305	87.02 300	87.79 332	94.77 280	77.27 314	87.90 326	93.21 294	81.74 297	89.99 307	88.39 369	83.47 248	96.93 305	71.29 376	92.43 371	89.15 386

GA-MVS		87.70 291	86.82 302	90.31 280	93.27 314	77.22 315	84.72 376	92.79 300	85.11 253	89.82 310	90.07 347	66.80 354	97.76 258	84.56 270	94.27 338	95.96 283

TinyColmap		92.00 197	92.76 172	89.71 296	95.62 252	77.02 316	90.72 256	96.17 215	87.70 207	95.26 156	96.29 176	92.54 113	96.45 321	81.77 295	98.77 145	95.66 299

Patchmtry		90.11 242	89.92 241	90.66 272	90.35 373	77.00 317	92.96 177	92.81 298	90.25 154	94.74 182	96.93 130	67.11 351	97.52 272	85.17 257	98.98 112	97.46 208

DIV-MVS_self_test		90.65 221	90.56 228	90.91 265	91.85 349	76.99 318	86.75 348	95.36 246	85.52 246	94.06 200	94.89 240	77.37 305	97.99 233	90.28 157	98.97 117	97.76 188

cl____		90.65 221	90.56 228	90.91 265	91.85 349	76.98 319	86.75 348	95.36 246	85.53 244	94.06 200	94.89 240	77.36 306	97.98 234	90.27 158	98.98 112	97.76 188

pmmvs5		87.87 288	87.14 296	90.07 288	93.26 315	76.97 320	88.89 311	92.18 312	73.71 358	88.36 335	93.89 278	76.86 314	96.73 313	80.32 308	96.81 275	96.51 253

eth_miper_zixun_eth		90.72 218	90.61 226	91.05 257	92.04 344	76.84 321	86.91 343	96.67 187	85.21 249	94.41 189	93.92 276	79.53 285	98.26 209	89.76 174	97.02 265	98.06 150

c3_l		91.32 211	91.42 207	91.00 261	92.29 334	76.79 322	87.52 334	96.42 202	85.76 237	94.72 184	93.89 278	82.73 259	98.16 218	90.93 139	98.55 167	98.04 153

test_vis1_n_1920		89.45 256	89.85 243	88.28 323	93.59 310	76.71 323	90.67 258	97.78 100	79.67 315	90.30 301	96.11 188	76.62 315	92.17 379	90.31 155	93.57 352	95.96 283

MVSTER		89.32 259	88.75 262	91.03 258	90.10 376	76.62 324	90.85 251	94.67 267	82.27 291	95.24 159	95.79 202	61.09 382	98.49 186	90.49 147	98.26 195	97.97 165

miper_ehance_all_eth		90.48 225	90.42 231	90.69 271	91.62 356	76.57 325	86.83 346	96.18 214	83.38 272	94.06 200	92.66 310	82.20 265	98.04 225	89.79 173	97.02 265	97.45 209

cl22		89.02 265	88.50 265	90.59 274	89.76 378	76.45 326	86.62 353	94.03 277	82.98 283	92.65 248	92.49 311	72.05 333	97.53 271	88.93 196	97.02 265	97.78 186

cascas		87.02 311	86.28 313	89.25 305	91.56 358	76.45 326	84.33 380	96.78 179	71.01 375	86.89 354	85.91 384	81.35 273	96.94 303	83.09 281	95.60 302	94.35 338

ADS-MVSNet2		84.01 333	82.20 344	89.41 300	89.04 386	76.37 328	87.57 329	90.98 328	72.71 366	84.46 369	92.45 312	68.08 347	96.48 319	70.58 382	83.97 396	95.38 307

EU-MVSNet		87.39 301	86.71 305	89.44 299	93.40 312	76.11 329	94.93 112	90.00 335	57.17 404	95.71 131	97.37 90	64.77 367	97.68 265	92.67 96	94.37 335	94.52 334

MIMVSNet		87.13 309	86.54 308	88.89 310	96.05 221	76.11 329	94.39 130	88.51 341	81.37 300	88.27 337	96.75 143	72.38 331	95.52 342	65.71 393	95.47 306	95.03 317

IterMVS		90.18 238	90.16 235	90.21 285	93.15 316	75.98 331	87.56 331	92.97 296	86.43 224	94.09 197	96.40 165	78.32 295	97.43 278	87.87 219	94.69 329	97.23 225
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MVS_Test		92.57 183	93.29 159	90.40 279	93.53 311	75.85 332	92.52 193	96.96 164	88.73 182	92.35 262	96.70 149	90.77 154	98.37 201	92.53 99	95.49 305	96.99 236

IB-MVS	77.21 19	83.11 339	81.05 351	89.29 303	91.15 362	75.85 332	85.66 367	86.00 364	79.70 314	82.02 390	86.61 379	48.26 399	98.39 194	77.84 333	92.22 372	93.63 355
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
VPNet		93.08 162	93.76 144	91.03 258	98.60 38	75.83 334	91.51 237	95.62 230	91.84 108	95.74 128	97.10 119	89.31 179	98.32 203	85.07 264	99.06 101	98.93 66

miper_enhance_ethall		88.42 280	87.87 283	90.07 288	88.67 390	75.52 335	85.10 371	95.59 235	75.68 343	92.49 253	89.45 358	78.96 288	97.88 242	87.86 220	97.02 265	96.81 244

Anonymous20240521		92.86 172	93.57 153	90.74 270	96.57 176	75.50 336	94.15 139	95.60 231	89.38 168	95.90 119	97.90 61	80.39 281	97.96 235	92.60 98	99.68 17	98.75 89

thisisatest0515		84.72 327	82.99 337	89.90 292	92.96 322	75.33 337	84.36 379	83.42 384	77.37 334	88.27 337	86.65 378	53.94 394	98.72 153	82.56 286	97.40 253	95.67 298

PS-MVSNAJ		88.86 272	88.99 257	88.48 320	94.88 273	74.71 338	86.69 350	95.60 231	80.88 305	87.83 343	87.37 376	90.77 154	98.82 132	82.52 287	94.37 335	91.93 375

WTY-MVS		86.93 312	86.50 311	88.24 324	94.96 271	74.64 339	87.19 338	92.07 317	78.29 329	88.32 336	91.59 331	78.06 297	94.27 365	74.88 355	93.15 361	95.80 291

xiu_mvs_v2_base		89.00 268	89.19 251	88.46 321	94.86 275	74.63 340	86.97 341	95.60 231	80.88 305	87.83 343	88.62 366	91.04 149	98.81 137	82.51 288	94.38 334	91.93 375

1314		86.46 315	86.33 312	86.87 342	91.65 355	74.54 341	91.94 222	94.10 276	74.28 354	84.78 368	87.33 377	83.03 254	95.00 354	78.72 328	91.16 380	91.06 382

CHOSEN 280x420		80.04 365	77.97 372	86.23 352	90.13 375	74.53 342	72.87 401	89.59 337	66.38 393	76.29 402	85.32 389	56.96 389	95.36 348	69.49 385	94.72 328	88.79 389

USDC		89.02 265	89.08 253	88.84 311	95.07 270	74.50 343	88.97 309	96.39 203	73.21 361	93.27 225	96.28 178	82.16 266	96.39 323	77.55 336	98.80 140	95.62 302

MVE	59.87 23	73.86 373	72.65 376	77.47 385	87.00 400	74.35 344	61.37 405	60.93 411	67.27 390	69.69 406	86.49 381	81.24 277	72.33 408	56.45 404	83.45 398	85.74 396
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EPNet_dtu		85.63 319	84.37 325	89.40 301	86.30 401	74.33 345	91.64 235	88.26 343	84.84 259	72.96 405	89.85 348	71.27 337	97.69 264	76.60 344	97.62 242	96.18 274
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline1		87.62 295	87.31 290	88.54 317	94.71 285	74.27 346	93.10 174	88.20 345	86.20 228	92.18 268	93.04 298	73.21 328	95.52 342	79.32 324	85.82 394	95.83 290

Patchmatch-test		86.10 317	86.01 314	86.38 350	90.63 368	74.22 347	89.57 293	86.69 358	85.73 238	89.81 311	92.83 303	65.24 365	91.04 384	77.82 335	95.78 299	93.88 349

dcpmvs_2		93.96 137	95.01 100	90.82 268	97.60 120	74.04 348	93.68 157	98.85 9	89.80 161	97.82 30	97.01 126	91.14 148	99.21 80	90.56 146	98.59 164	99.19 34

MDA-MVSNet_test_wron		88.16 285	88.23 276	87.93 329	92.22 336	73.71 349	80.71 394	88.84 338	82.52 288	94.88 177	95.14 230	82.70 260	93.61 370	83.28 279	93.80 349	96.46 259

YYNet1		88.17 284	88.24 275	87.93 329	92.21 337	73.62 350	80.75 393	88.77 339	82.51 289	94.99 172	95.11 232	82.70 260	93.70 369	83.33 278	93.83 348	96.48 257

test0.0.03 1		82.48 345	81.47 349	85.48 356	89.70 379	73.57 351	84.73 374	81.64 389	83.07 281	88.13 339	86.61 379	62.86 376	89.10 396	66.24 392	90.29 384	93.77 351

thres600view7		87.66 293	87.10 299	89.36 302	96.05 221	73.17 352	92.72 184	85.31 373	91.89 103	93.29 223	90.97 338	63.42 373	98.39 194	73.23 365	96.99 270	96.51 253

ANet_high		94.83 100	96.28 39	90.47 276	96.65 170	73.16 353	94.33 132	98.74 13	96.39 27	98.09 27	98.93 8	93.37 88	98.70 160	90.38 151	99.68 17	99.53 14

thres100view900		87.35 302	86.89 301	88.72 313	96.14 214	73.09 354	93.00 176	85.31 373	92.13 96	93.26 226	90.96 339	63.42 373	98.28 205	71.27 377	96.54 283	94.79 327

tfpn200view9		87.05 310	86.52 309	88.67 314	95.77 241	72.94 355	91.89 225	86.00 364	90.84 137	92.61 249	89.80 350	63.93 370	98.28 205	71.27 377	96.54 283	94.79 327

thres400		87.20 306	86.52 309	89.24 306	95.77 241	72.94 355	91.89 225	86.00 364	90.84 137	92.61 249	89.80 350	63.93 370	98.28 205	71.27 377	96.54 283	96.51 253

baseline2		83.38 338	81.54 348	88.90 309	91.38 359	72.84 357	88.78 315	81.22 392	78.97 324	79.82 398	87.56 373	61.73 380	97.80 251	74.30 359	90.05 385	96.05 280

ECVR-MVS		90.12 241	90.16 235	90.00 291	97.81 103	72.68 358	95.76 78	78.54 402	89.04 175	95.36 149	98.10 43	70.51 340	98.64 170	87.10 231	99.18 92	98.67 102

thres200		85.85 318	85.18 319	87.88 331	94.44 291	72.52 359	89.08 308	86.21 361	88.57 188	91.44 280	88.40 368	64.22 368	98.00 231	68.35 386	95.88 298	93.12 362

MG-MVS		89.54 254	89.80 244	88.76 312	94.88 273	72.47 360	89.60 292	92.44 309	85.82 235	89.48 316	95.98 194	82.85 257	97.74 261	81.87 294	95.27 313	96.08 278

PAPM		81.91 352	80.11 362	87.31 336	93.87 305	72.32 361	84.02 382	93.22 292	69.47 385	76.13 403	89.84 349	72.15 332	97.23 287	53.27 405	89.02 387	92.37 372

SCA		87.43 300	87.21 294	88.10 327	92.01 345	71.98 362	89.43 298	88.11 347	82.26 292	88.71 329	92.83 303	78.65 291	97.59 269	79.61 321	93.30 357	94.75 329

testgi		90.38 231	91.34 210	87.50 334	97.49 127	71.54 363	89.43 298	95.16 250	88.38 192	94.54 187	94.68 250	92.88 106	93.09 375	71.60 375	97.85 230	97.88 174

test1111		90.39 230	90.61 226	89.74 295	98.04 86	71.50 364	95.59 84	79.72 399	89.41 167	95.94 116	98.14 41	70.79 338	98.81 137	88.52 206	99.32 67	98.90 72

gg-mvs-nofinetune		82.10 350	81.02 352	85.34 357	87.46 396	71.04 365	94.74 116	67.56 409	96.44 26	79.43 399	98.99 6	45.24 402	96.15 329	67.18 390	92.17 373	88.85 388

GG-mvs-BLEND				83.24 374	85.06 406	71.03 366	94.99 111	65.55 410		74.09 404	75.51 404	44.57 404	94.46 361	59.57 401	87.54 391	84.24 397

ppachtmachnet_test		88.61 278	88.64 263	88.50 319	91.76 351	70.99 367	84.59 377	92.98 295	79.30 322	92.38 260	93.53 289	79.57 284	97.45 277	86.50 244	97.17 260	97.07 230

our_test_3		87.55 297	87.59 287	87.44 335	91.76 351	70.48 368	83.83 383	90.55 333	79.79 312	92.06 272	92.17 320	78.63 293	95.63 340	84.77 267	94.73 327	96.22 272

CVMVSNet		85.16 323	84.72 321	86.48 346	92.12 341	70.19 369	92.32 206	88.17 346	56.15 405	90.64 294	95.85 198	67.97 349	96.69 314	88.78 201	90.52 383	92.56 370

new_pmnet		81.22 355	81.01 353	81.86 377	90.92 366	70.15 370	84.03 381	80.25 398	70.83 376	85.97 358	89.78 353	67.93 350	84.65 403	67.44 389	91.90 376	90.78 383

KD-MVS_2432*1600		82.17 348	80.75 355	86.42 348	82.04 410	70.09 371	81.75 390	90.80 330	82.56 286	90.37 299	89.30 359	42.90 408	96.11 331	74.47 357	92.55 369	93.06 363

miper_refine_blended		82.17 348	80.75 355	86.42 348	82.04 410	70.09 371	81.75 390	90.80 330	82.56 286	90.37 299	89.30 359	42.90 408	96.11 331	74.47 357	92.55 369	93.06 363

DSMNet-mixed		82.21 347	81.56 346	84.16 368	89.57 382	70.00 373	90.65 259	77.66 404	54.99 406	83.30 381	97.57 74	77.89 299	90.50 387	66.86 391	95.54 304	91.97 374

PatchmatchNet		85.22 322	84.64 322	86.98 339	89.51 383	69.83 374	90.52 262	87.34 355	78.87 326	87.22 352	92.74 307	66.91 353	96.53 316	81.77 295	86.88 392	94.58 333
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EMVS		80.35 363	80.28 361	80.54 381	84.73 407	69.07 375	72.54 402	80.73 395	87.80 203	81.66 392	81.73 398	62.89 375	89.84 390	75.79 352	94.65 330	82.71 400

E-PMN		80.72 360	80.86 354	80.29 382	85.11 405	68.77 376	72.96 400	81.97 388	87.76 205	83.25 382	83.01 397	62.22 379	89.17 395	77.15 341	94.31 337	82.93 399

testing222		80.54 362	78.53 369	86.58 345	92.54 330	68.60 377	86.24 359	82.72 386	83.78 271	82.68 385	84.24 393	39.25 412	95.94 336	60.25 399	95.09 318	95.20 309

mvs_anonymous		90.37 232	91.30 211	87.58 333	92.17 340	68.00 378	89.84 286	94.73 264	83.82 270	93.22 230	97.40 88	87.54 200	97.40 281	87.94 218	95.05 319	97.34 219

testing91		83.56 337	82.45 341	86.91 341	92.92 323	67.29 379	86.33 358	88.07 348	86.22 227	84.26 372	85.76 385	48.15 400	97.17 292	76.27 348	94.08 346	96.27 269

testing11		81.98 351	80.52 358	86.38 350	92.69 325	67.13 380	85.79 365	84.80 378	82.16 293	81.19 395	85.41 388	45.24 402	96.88 308	74.14 360	93.24 358	95.14 313

CostFormer		83.09 340	82.21 343	85.73 353	89.27 385	67.01 381	90.35 269	86.47 360	70.42 380	83.52 379	93.23 296	61.18 381	96.85 309	77.21 340	88.26 390	93.34 361

PatchT		87.51 298	88.17 279	85.55 355	90.64 367	66.91 382	92.02 218	86.09 363	92.20 94	89.05 321	97.16 112	64.15 369	96.37 325	89.21 191	92.98 365	93.37 360

test-LLR		83.58 336	83.17 335	84.79 363	89.68 380	66.86 383	83.08 385	84.52 379	83.07 281	82.85 383	84.78 391	62.86 376	93.49 371	82.85 282	94.86 323	94.03 344

test-mter		81.21 356	80.01 363	84.79 363	89.68 380	66.86 383	83.08 385	84.52 379	73.85 357	82.85 383	84.78 391	43.66 407	93.49 371	82.85 282	94.86 323	94.03 344

testing99		82.94 342	81.72 345	86.59 344	92.55 328	66.53 385	86.08 362	85.70 367	85.47 247	83.95 374	85.70 386	45.87 401	97.07 298	76.58 345	93.56 353	96.17 276

test2506		85.42 321	84.57 324	87.96 328	97.81 103	66.53 385	96.14 61	56.35 412	89.04 175	93.55 216	98.10 43	42.88 410	98.68 164	88.09 213	99.18 92	98.67 102

PVSNet_0	70.34 21	74.58 372	72.96 375	79.47 383	90.63 368	66.24 387	73.26 399	83.40 385	63.67 400	78.02 400	78.35 403	72.53 329	89.59 392	56.68 402	60.05 407	82.57 401

ETVMVS		79.85 366	77.94 373	85.59 354	92.97 321	66.20 388	86.13 361	80.99 394	81.41 299	83.52 379	83.89 394	41.81 411	94.98 357	56.47 403	94.25 339	95.61 303

WB-MVSnew		84.20 332	83.89 331	85.16 360	91.62 356	66.15 389	88.44 323	81.00 393	76.23 342	87.98 341	87.77 372	84.98 239	93.35 373	62.85 398	94.10 345	95.98 282

testing3		83.66 335	82.52 340	87.08 337	95.84 235	65.84 390	89.80 288	77.17 406	88.17 196	90.84 290	88.63 365	30.95 414	98.11 221	84.05 274	97.19 259	97.28 223

ADS-MVSNet		82.25 346	81.55 347	84.34 367	89.04 386	65.30 391	87.57 329	85.13 377	72.71 366	84.46 369	92.45 312	68.08 347	92.33 378	70.58 382	83.97 396	95.38 307

tpmvs		84.22 331	83.97 329	84.94 361	87.09 398	65.18 392	91.21 244	88.35 342	82.87 284	85.21 361	90.96 339	65.24 365	96.75 312	79.60 323	85.25 395	92.90 367

tpm2		81.46 353	80.35 360	84.80 362	89.90 377	65.14 393	90.44 264	85.36 372	65.82 396	82.05 389	92.44 314	57.94 387	96.69 314	70.71 381	88.49 389	92.56 370

EPMVS		81.17 357	80.37 359	83.58 372	85.58 404	65.08 394	90.31 271	71.34 408	77.31 335	85.80 359	91.30 333	59.38 385	92.70 377	79.99 314	82.34 401	92.96 366

tpm cat1		80.61 361	79.46 364	84.07 369	88.78 388	65.06 395	89.26 304	88.23 344	62.27 401	81.90 391	89.66 356	62.70 378	95.29 351	71.72 373	80.60 403	91.86 377

DeepMVS_CX				53.83 390	70.38 413	64.56 396		48.52 414	33.01 408	65.50 408	74.21 405	56.19 391	46.64 411	38.45 409	70.07 405	50.30 406

PVSNet	76.22 20	82.89 343	82.37 342	84.48 365	93.96 302	64.38 397	78.60 396	88.61 340	71.50 371	84.43 371	86.36 382	74.27 324	94.60 359	69.87 384	93.69 351	94.46 335

TESTMET0.1,1		79.09 369	78.04 371	82.25 376	87.52 395	64.03 398	83.08 385	80.62 396	70.28 381	80.16 397	83.22 396	44.13 405	90.56 386	79.95 315	93.36 355	92.15 373

tpm		84.38 330	84.08 328	85.30 358	90.47 371	63.43 399	89.34 301	85.63 369	77.24 336	87.62 347	95.03 236	61.00 383	97.30 285	79.26 325	91.09 381	95.16 311

Syy-MVS		84.81 326	84.93 320	84.42 366	91.71 353	63.36 400	85.89 363	81.49 390	81.03 302	85.13 363	81.64 399	77.44 302	95.00 354	85.94 251	94.12 343	94.91 323

MDTV_nov1_ep13			83.88 332		89.42 384	61.52 401	88.74 317	87.41 353	73.99 356	84.96 367	94.01 273	65.25 364	95.53 341	78.02 331	93.16 360

WAC-MVS						61.25 402								74.55 356

myMVS_eth3d		79.62 367	78.26 370	83.72 371	91.71 353	61.25 402	85.89 363	81.49 390	81.03 302	85.13 363	81.64 399	32.12 413	95.00 354	71.17 380	94.12 343	94.91 323

UWE-MVS		80.29 364	79.10 365	83.87 370	91.97 347	59.56 404	86.50 357	77.43 405	75.40 347	87.79 345	88.10 370	44.08 406	96.90 307	64.23 394	96.36 287	95.14 313

gm-plane-assit					87.08 399	59.33 405			71.22 372		83.58 395		97.20 289	73.95 361

tpmrst		82.85 344	82.93 338	82.64 375	87.65 393	58.99 406	90.14 276	87.90 350	75.54 345	83.93 375	91.63 330	66.79 356	95.36 348	81.21 303	81.54 402	93.57 359

dp		79.28 368	78.62 368	81.24 380	85.97 403	56.45 407	86.91 343	85.26 375	72.97 364	81.45 394	89.17 363	56.01 392	95.45 346	73.19 366	76.68 404	91.82 378

new-patchmatchnet		88.97 269	90.79 222	83.50 373	94.28 295	55.83 408	85.34 370	93.56 286	86.18 229	95.47 141	95.73 208	83.10 252	96.51 318	85.40 256	98.06 214	98.16 144

dmvs_testset		78.23 371	78.99 366	75.94 386	91.99 346	55.34 409	88.86 312	78.70 401	82.69 285	81.64 393	79.46 401	75.93 318	85.74 401	48.78 407	82.85 400	86.76 394

SSC-MVS		90.16 239	92.96 165	81.78 378	97.88 97	48.48 410	90.75 254	87.69 351	96.02 34	96.70 81	97.63 71	85.60 233	97.80 251	85.73 253	98.60 163	99.06 48

WB-MVS		89.44 257	92.15 189	81.32 379	97.73 110	48.22 411	89.73 289	87.98 349	95.24 39	96.05 112	96.99 127	85.18 236	96.95 302	82.45 289	97.97 223	98.78 85

MVS-HIRNet		78.83 370	80.60 357	73.51 388	93.07 317	47.37 412	87.10 340	78.00 403	68.94 386	77.53 401	97.26 102	71.45 336	94.62 358	63.28 397	88.74 388	78.55 403

PMMVS2		81.31 354	83.44 333	74.92 387	90.52 370	46.49 413	69.19 403	85.23 376	84.30 266	87.95 342	94.71 249	76.95 311	84.36 404	64.07 395	98.09 212	93.89 348

MDTV_nov1_ep13_2view						42.48 414	88.45 322		67.22 391	83.56 378		66.80 354		72.86 368		94.06 343

dongtai		53.72 374	53.79 377	53.51 391	79.69 412	36.70 415	77.18 397	32.53 417	71.69 369	68.63 407	60.79 406	26.65 415	73.11 407	30.67 410	36.29 409	50.73 405

kuosan		43.63 376	44.25 380	41.78 392	66.04 414	34.37 416	75.56 398	32.62 416	53.25 407	50.46 410	51.18 407	25.28 416	49.13 410	13.44 411	30.41 410	41.84 407

tmp_tt		37.97 377	44.33 379	18.88 393	11.80 416	21.54 417	63.51 404	45.66 415	4.23 410	51.34 409	50.48 408	59.08 386	22.11 412	44.50 408	68.35 406	13.00 408

test_method		50.44 375	48.94 378	54.93 389	39.68 415	12.38 418	28.59 406	90.09 334	6.82 409	41.10 411	78.41 402	54.41 393	70.69 409	50.12 406	51.26 408	81.72 402

test123		9.49 379	12.01 382	1.91 394	2.87 417	1.30 419	82.38 388	1.34 419	1.36 412	2.84 413	6.56 411	2.45 417	0.97 413	2.73 412	5.56 411	3.47 409

testmvs		9.02 380	11.42 383	1.81 395	2.77 418	1.13 420	79.44 395	1.90 418	1.18 413	2.65 414	6.80 410	1.95 418	0.87 414	2.62 413	3.45 412	3.44 410

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

cdsmvs_eth3d_5k		23.35 378	31.13 381	0.00 396	0.00 419	0.00 421	0.00 407	95.58 237	0.00 414	0.00 415	91.15 335	93.43 86	0.00 415	0.00 414	0.00 413	0.00 411

pcd_1.5k_mvsjas		7.56 381	10.09 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	90.77 154	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		7.56 381	10.08 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	90.69 344	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

PC_three_1452									75.31 349	95.87 121	95.75 207	92.93 103	96.34 328	87.18 230	98.68 155	98.04 153

eth-test2					0.00 419

eth-test					0.00 419

test_241102_TWO								98.10 58	91.95 99	97.54 41	97.25 103	95.37 30	99.35 60	93.29 75	99.25 81	98.49 122

9.14			94.81 105		97.49 127		94.11 142	98.37 22	87.56 211	95.38 146	96.03 192	94.66 62	99.08 96	90.70 143	98.97 117

test_0728_THIRD									93.26 74	97.40 52	97.35 96	94.69 61	99.34 63	93.88 48	99.42 50	98.89 73

GSMVS																94.75 329

sam_mvs1												66.64 357				94.75 329

sam_mvs												66.41 358

MTGPA								97.62 109

test_post1							90.21 273				5.85 413	65.36 363	96.00 334	79.61 321

test_post											6.07 412	65.74 362	95.84 338

patchmatchnet-post											91.71 328	66.22 360	97.59 269

MTMP							94.82 114	54.62 413

test9_res														88.16 211	98.40 179	97.83 180

agg_prior2														87.06 233	98.36 188	97.98 162

test_prior2							90.21 273		89.33 170	90.77 291	94.81 243	90.41 164		88.21 207	98.55 167

旧先验2							90.00 281		68.65 387	92.71 247			96.52 317	85.15 259

新几何2							90.02 280

无先验							89.94 282	95.75 227	70.81 377				98.59 176	81.17 304		94.81 325

原ACMM2							89.34 301

testdata2													98.03 226	80.24 311

segment_acmp												92.14 121

testdata1							88.96 310		88.44 191

plane_prior5								97.81 95					98.95 116	89.26 188	98.51 173	98.60 114

plane_prior4											95.59 212

plane_prior2							94.56 125		91.74 116

plane_prior1					97.38 132

n2								0.00 420

nn								0.00 420

door-mid								92.13 316

test11								96.65 188

door								91.26 325

HQP-NCC					96.36 191		91.37 239		87.16 215	88.81 324

ACMP_Plane					96.36 191		91.37 239		87.16 215	88.81 324

BP-MVS														86.55 242

HQP4-MVS										88.81 324			98.61 172			98.15 145

HQP3-MVS								97.31 138							97.73 234

HQP2-MVS												84.76 240

ACMMP++_ref															98.82 137

ACMMP++															99.25 81

Test By Simon												90.61 160

High-resolution multi-view benchmark