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 74	99.36 1	96.10 63	99.32 2	98.75 2	99.58 2	98.70 20	91.78 133	99.88 1	98.60 1	99.67 20	98.54 125

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

PMVS	87.21 14	94.97 100	95.33 93	93.91 153	98.97 17	97.16 3	95.54 92	95.85 236	96.47 25	93.40 233	97.46 97	95.31 37	95.47 362	86.18 263	98.78 149	89.11 409
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testf1		96.77 18	96.49 30	97.60 10	99.01 14	96.70 4	96.31 52	98.33 30	94.96 45	97.30 57	97.93 57	96.05 16	97.90 248	89.32 196	99.23 87	98.19 155

APD_test2		96.77 18	96.49 30	97.60 10	99.01 14	96.70 4	96.31 52	98.33 30	94.96 45	97.30 57	97.93 57	96.05 16	97.90 248	89.32 196	99.23 87	98.19 155

Effi-MVS+-dtu		93.90 150	92.60 189	97.77 4	94.74 295	96.67 6	94.00 151	95.41 255	89.94 166	91.93 290	92.13 339	90.12 176	98.97 117	87.68 236	97.48 263	97.67 214

APD_test1		95.91 57	95.42 88	97.36 27	98.82 25	96.62 7	95.64 84	97.64 115	93.38 76	95.89 130	97.23 117	93.35 93	97.66 277	88.20 222	98.66 166	97.79 203

RPSCF		95.58 72	94.89 109	97.62 9	97.58 124	96.30 8	95.97 70	97.53 128	92.42 89	93.41 230	97.78 68	91.21 149	97.77 267	91.06 147	97.06 278	98.80 89

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 59	98.46 33	94.62 66	98.84 134	94.64 43	99.53 37	98.99 59

SR-MVS-dyc-post		96.84 11	96.60 28	97.56 14	98.07 84	95.27 10	96.37 46	98.12 61	95.66 39	97.00 72	97.03 136	94.85 60	99.42 36	93.49 73	98.84 136	98.00 172

RE-MVS-def			96.66 23		98.07 84	95.27 10	96.37 46	98.12 61	95.66 39	97.00 72	97.03 136	95.40 31		93.49 73	98.84 136	98.00 172

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 26	99.35 60	98.52 128

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 68	95.47 28	99.50 22	95.26 36	99.33 66	98.36 139

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 68	95.47 28	99.50 22	95.26 36	99.33 66	98.36 139

SR-MVS		96.70 23	96.42 33	97.54 15	98.05 86	94.69 15	96.13 62	98.07 71	95.17 43	96.82 83	96.73 159	95.09 49	99.43 35	92.99 99	98.71 158	98.50 129

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

mPP-MVS		96.46 35	96.05 55	97.69 6	98.62 35	94.65 17	96.45 41	97.74 110	92.59 87	95.47 151	96.68 162	94.50 71	99.42 36	93.10 94	99.26 83	98.99 59

CP-MVS		96.44 38	96.08 53	97.54 15	98.29 68	94.62 18	96.80 24	98.08 68	92.67 86	95.08 179	96.39 181	94.77 62	99.42 36	93.17 92	99.44 49	98.58 122

EGC-MVSNET		80.97 377	75.73 395	96.67 46	98.85 23	94.55 19	96.83 22	96.60 201	2.44 433	5.32 434	98.25 40	92.24 122	98.02 238	91.85 128	99.21 91	97.45 228

FPMVS		84.50 346	83.28 353	88.16 338	96.32 209	94.49 20	85.76 384	85.47 390	83.09 297	85.20 381	94.26 279	63.79 386	86.58 422	63.72 416	91.88 398	83.40 420

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 32	96.69 19	96.86 79	97.56 85	95.48 27	98.77 151	90.11 179	99.44 49	98.31 146
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
XVG-OURS		94.72 110	94.12 145	96.50 51	98.00 92	94.23 22	91.48 252	98.17 55	90.72 150	95.30 162	96.47 171	87.94 205	96.98 316	91.41 143	97.61 258	98.30 147

LS3D		96.11 51	95.83 70	96.95 40	94.75 294	94.20 23	97.34 13	97.98 86	97.31 12	95.32 161	96.77 152	93.08 103	99.20 87	91.79 130	98.16 216	97.44 230

XVG-OURS-SEG-HR		95.38 81	95.00 107	96.51 50	98.10 82	94.07 24	92.46 208	98.13 60	90.69 151	93.75 221	96.25 194	98.03 2	97.02 315	92.08 120	95.55 322	98.45 134

MP-MVS		96.14 50	95.68 77	97.51 17	98.81 27	94.06 25	96.10 63	97.78 108	92.73 83	93.48 228	96.72 160	94.23 76	99.42 36	91.99 123	99.29 76	99.05 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PM-MVS		93.33 163	92.67 187	95.33 88	96.58 183	94.06 25	92.26 222	92.18 326	85.92 250	96.22 113	96.61 166	85.64 242	95.99 352	90.35 167	98.23 209	95.93 303

MSP-MVS		95.34 83	94.63 126	97.48 18	98.67 32	94.05 27	96.41 45	98.18 51	91.26 138	95.12 175	95.15 243	86.60 230	99.50 22	93.43 82	96.81 290	98.89 78
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 26	96.38 37	97.47 19	98.95 18	94.05 27	95.88 74	97.62 117	94.46 54	96.29 107	96.94 142	93.56 85	99.37 60	94.29 51	99.42 51	98.99 59

anonymousdsp		96.74 21	96.42 33	97.68 8	98.00 92	94.03 29	96.97 19	97.61 119	87.68 218	98.45 19	98.77 17	94.20 77	99.50 22	96.70 10	99.40 56	99.53 17

XVS		96.49 33	96.18 46	97.44 20	98.56 41	93.99 30	96.50 37	97.95 91	94.58 50	94.38 202	96.49 170	94.56 69	99.39 52	93.57 69	99.05 107	98.93 71

X-MVStestdata		90.70 231	88.45 280	97.44 20	98.56 41	93.99 30	96.50 37	97.95 91	94.58 50	94.38 202	26.89 431	94.56 69	99.39 52	93.57 69	99.05 107	98.93 71

HPM-MVS_fast		97.01 10	96.89 18	97.39 25	99.12 8	93.92 32	97.16 14	98.17 55	93.11 80	96.48 97	97.36 104	96.92 6	99.34 65	94.31 50	99.38 58	98.92 75

ACMMP		96.61 28	96.34 38	97.43 22	98.61 37	93.88 33	96.95 20	98.18 51	92.26 96	96.33 102	96.84 150	95.10 48	99.40 49	93.47 76	99.33 66	99.02 56
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 6	98.22 75	93.87 34	98.42 6	98.19 49	96.95 16	95.46 153	99.23 6	93.45 88	99.57 15	95.34 35	99.89 2	99.63 12

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 8	99.77 9	99.31 30
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 44	95.94 61	97.43 22	98.59 40	93.84 36	95.33 98	98.30 35	91.40 135	95.76 135	96.87 147	95.26 39	99.45 31	92.77 102	99.21 91	99.00 57

APD-MVS_3200maxsize		96.82 13	96.65 24	97.32 29	97.95 96	93.82 37	96.31 52	98.25 39	95.51 41	96.99 74	97.05 135	95.63 23	99.39 52	93.31 85	98.88 131	98.75 95

ACMMPR		96.46 35	96.14 49	97.41 24	98.60 38	93.82 37	96.30 56	97.96 89	92.35 93	95.57 146	96.61 166	94.93 58	99.41 42	93.78 63	99.15 99	99.00 57

region2R		96.41 40	96.09 51	97.38 26	98.62 35	93.81 39	96.32 51	97.96 89	92.26 96	95.28 165	96.57 168	95.02 52	99.41 42	93.63 67	99.11 102	98.94 69

N_pmnet		88.90 284	87.25 307	93.83 158	94.40 306	93.81 39	84.73 392	87.09 372	79.36 339	93.26 240	92.43 333	79.29 297	91.68 400	77.50 355	97.22 273	96.00 299

HPM-MVS++		95.02 98	94.39 132	96.91 41	97.88 100	93.58 41	94.09 149	96.99 174	91.05 143	92.40 274	95.22 242	91.03 156	99.25 81	92.11 118	98.69 161	97.90 187

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	95.95 125	96.41 176	96.71 8	99.42 36	93.99 58	99.36 59	99.13 43
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
HFP-MVS		96.39 42	96.17 48	97.04 35	98.51 49	93.37 43	96.30 56	97.98 86	92.35 93	95.63 143	96.47 171	95.37 32	99.27 80	93.78 63	99.14 100	98.48 132

ITE_SJBPF				95.95 61	97.34 137	93.36 44		96.55 208	91.93 107	94.82 189	95.39 239	91.99 128	97.08 312	85.53 269	97.96 238	97.41 231

XVG-ACMP-BASELINE		95.68 68	95.34 92	96.69 45	98.40 59	93.04 45	94.54 133	98.05 75	90.45 159	96.31 105	96.76 154	92.91 109	98.72 157	91.19 145	99.42 51	98.32 144

CPTT-MVS		94.74 109	94.12 145	96.60 47	98.15 79	93.01 46	95.84 76	97.66 114	89.21 183	93.28 238	95.46 232	88.89 190	98.98 113	89.80 186	98.82 142	97.80 202

DeepPCF-MVS	90.46 6	94.20 139	93.56 164	96.14 55	95.96 241	92.96 47	89.48 312	97.46 134	85.14 269	96.23 112	95.42 235	93.19 98	98.08 230	90.37 166	98.76 152	97.38 237

ACMM	88.83 9	96.30 46	96.07 54	96.97 38	98.39 60	92.95 48	94.74 121	98.03 80	90.82 148	97.15 64	96.85 148	96.25 14	99.00 112	93.10 94	99.33 66	98.95 68
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PatchMatch-RL		89.18 273	88.02 296	92.64 208	95.90 245	92.87 49	88.67 336	91.06 341	80.34 325	90.03 323	91.67 347	83.34 259	94.42 380	76.35 364	94.84 344	90.64 406

ZNCC-MVS		96.42 39	96.20 45	97.07 34	98.80 29	92.79 50	96.08 65	98.16 58	91.74 122	95.34 160	96.36 184	95.68 21	99.44 32	94.41 48	99.28 81	98.97 65

GST-MVS		96.24 47	95.99 59	97.00 37	98.65 33	92.71 51	95.69 82	98.01 83	92.08 103	95.74 138	96.28 190	95.22 42	99.42 36	93.17 92	99.06 104	98.88 80

mvs_tets		96.83 12	96.71 22	97.17 31	98.83 24	92.51 52	96.58 33	97.61 119	87.57 220	98.80 8	98.90 11	96.50 9	99.59 14	96.15 18	99.47 42	99.40 24

jajsoiax		96.59 31	96.42 33	97.12 33	98.76 30	92.49 53	96.44 43	97.42 136	86.96 232	98.71 11	98.72 19	95.36 34	99.56 18	95.92 19	99.45 46	99.32 29

AllTest		94.88 104	94.51 130	96.00 58	98.02 90	92.17 54	95.26 102	98.43 21	90.48 157	95.04 180	96.74 157	92.54 118	97.86 256	85.11 276	98.98 116	97.98 176

TestCases				96.00 58	98.02 90	92.17 54		98.43 21	90.48 157	95.04 180	96.74 157	92.54 118	97.86 256	85.11 276	98.98 116	97.98 176

LPG-MVS_test		96.38 43	96.23 43	96.84 42	98.36 66	92.13 56	95.33 98	98.25 39	91.78 118	97.07 67	97.22 119	96.38 12	99.28 78	92.07 121	99.59 27	99.11 47

LGP-MVS_train				96.84 42	98.36 66	92.13 56		98.25 39	91.78 118	97.07 67	97.22 119	96.38 12	99.28 78	92.07 121	99.59 27	99.11 47

LF4IMVS		92.72 186	92.02 202	94.84 109	95.65 262	91.99 58	92.92 187	96.60 201	85.08 272	92.44 272	93.62 302	86.80 226	96.35 342	86.81 248	98.25 207	96.18 292

SteuartSystems-ACMMP		96.40 41	96.30 40	96.71 44	98.63 34	91.96 59	95.70 80	98.01 83	93.34 77	96.64 91	96.57 168	94.99 54	99.36 61	93.48 75	99.34 64	98.82 85
Skip Steuart: Steuart Systems R&D Blog.
F-COLMAP		92.28 200	91.06 227	95.95 61	97.52 127	91.90 60	93.53 166	97.18 159	83.98 285	88.70 349	94.04 287	88.41 195	98.55 185	80.17 330	95.99 311	97.39 235

OurMVSNet-221017-0		96.80 16	96.75 21	96.96 39	99.03 11	91.85 61	97.98 7	98.01 83	94.15 58	98.93 4	99.07 7	88.07 201	99.57 15	95.86 21	99.69 14	99.46 20

MAR-MVS		90.32 247	88.87 275	94.66 120	94.82 289	91.85 61	94.22 142	94.75 275	80.91 321	87.52 368	88.07 391	86.63 229	97.87 255	76.67 360	96.21 307	94.25 360
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 27	96.49 30	97.01 36	98.55 44	91.77 63	97.15 15	97.37 139	88.98 186	98.26 24	98.86 12	93.35 93	99.60 10	96.41 14	99.45 46	99.66 9

ACMP	88.15 13	95.71 67	95.43 87	96.54 49	98.17 78	91.73 64	94.24 140	98.08 68	89.46 175	96.61 93	96.47 171	95.85 18	99.12 96	90.45 162	99.56 34	98.77 94
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CS-MVS		95.77 64	95.58 81	96.37 54	96.84 164	91.72 65	96.73 28	99.06 8	94.23 56	92.48 269	94.79 261	93.56 85	99.49 28	93.47 76	99.05 107	97.89 189

PHI-MVS		94.34 130	93.80 152	95.95 61	95.65 262	91.67 66	94.82 119	97.86 97	87.86 212	93.04 250	94.16 284	91.58 138	98.78 148	90.27 172	98.96 123	97.41 231

ACMMP_NAP		96.21 48	96.12 50	96.49 52	98.90 19	91.42 67	94.57 129	98.03 80	90.42 160	96.37 100	97.35 107	95.68 21	99.25 81	94.44 47	99.34 64	98.80 89

OMC-MVS		94.22 138	93.69 157	95.81 71	97.25 140	91.27 68	92.27 221	97.40 138	87.10 230	94.56 197	95.42 235	93.74 83	98.11 227	86.62 253	98.85 135	98.06 164

MP-MVS-pluss		96.08 52	95.92 64	96.57 48	99.06 10	91.21 69	93.25 175	98.32 32	87.89 211	96.86 79	97.38 100	95.55 26	99.39 52	95.47 29	99.47 42	99.11 47
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SMA-MVS		95.77 64	95.54 82	96.47 53	98.27 70	91.19 70	95.09 109	97.79 107	86.48 237	97.42 52	97.51 94	94.47 74	99.29 74	93.55 71	99.29 76	98.93 71
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		91.72 212	91.20 222	93.26 185	96.17 223	91.02 71	91.14 260	95.55 249	90.16 164	90.87 305	93.56 305	86.31 233	94.40 381	79.92 336	97.12 276	94.37 357

OPM-MVS		95.61 70	95.45 85	96.08 57	98.49 56	91.00 72	92.65 199	97.33 147	90.05 165	96.77 86	96.85 148	95.04 50	98.56 183	92.77 102	99.06 104	98.70 104
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MVS_111021_LR		93.66 154	93.28 171	94.80 110	96.25 218	90.95 73	90.21 289	95.43 254	87.91 209	93.74 223	94.40 275	92.88 111	96.38 340	90.39 164	98.28 203	97.07 249

Gipuma		95.31 87	95.80 73	93.81 159	97.99 95	90.91 74	96.42 44	97.95 91	96.69 19	91.78 291	98.85 14	91.77 134	95.49 361	91.72 132	99.08 103	95.02 338
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
APD-MVS		95.00 99	94.69 120	95.93 64	97.38 134	90.88 75	94.59 126	97.81 103	89.22 182	95.46 153	96.17 199	93.42 91	99.34 65	89.30 198	98.87 134	97.56 222
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + GP.		93.07 174	92.41 193	95.06 102	95.82 250	90.87 76	90.97 265	92.61 319	88.04 208	94.61 196	93.79 298	88.08 200	97.81 261	89.41 195	98.39 192	96.50 275

3Dnovator+	92.74 2	95.86 61	95.77 74	96.13 56	96.81 167	90.79 77	96.30 56	97.82 102	96.13 32	94.74 193	97.23 117	91.33 144	99.16 90	93.25 89	98.30 202	98.46 133

SPE-MVS-test		95.32 84	95.10 103	95.96 60	96.86 162	90.75 78	96.33 49	99.20 5	93.99 60	91.03 304	93.73 299	93.52 87	99.55 19	91.81 129	99.45 46	97.58 219

hse-mvs2		92.24 203	91.20 222	95.38 85	96.16 224	90.65 79	92.52 204	92.01 333	89.23 180	93.95 216	92.99 318	76.88 323	98.69 166	91.02 148	96.03 309	96.81 263

h-mvs33		92.89 178	91.99 203	95.58 79	96.97 153	90.55 80	93.94 154	94.01 292	89.23 180	93.95 216	96.19 196	76.88 323	99.14 93	91.02 148	95.71 318	97.04 253

AUN-MVS		90.05 258	88.30 284	95.32 90	96.09 231	90.52 81	92.42 212	92.05 332	82.08 311	88.45 353	92.86 320	65.76 373	98.69 166	88.91 212	96.07 308	96.75 267

ZD-MVS					97.23 141	90.32 82		97.54 126	84.40 282	94.78 191	95.79 216	92.76 114	99.39 52	88.72 217	98.40 188

mvsany_test3		89.11 276	88.21 292	91.83 236	91.30 378	90.25 83	88.09 342	78.76 421	76.37 362	96.43 98	98.39 36	83.79 257	90.43 408	86.57 254	94.20 359	94.80 346

DeepC-MVS	91.39 4	95.43 77	95.33 93	95.71 76	97.67 119	90.17 84	93.86 156	98.02 82	87.35 222	96.22 113	97.99 54	94.48 73	99.05 105	92.73 105	99.68 17	97.93 183
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	90.40 240	88.92 272	94.85 108	96.53 190	90.02 85	91.58 249	96.48 211	80.16 327	86.14 376	92.18 337	85.73 239	98.25 214	76.87 359	94.61 350	96.30 284
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_prior4						89.91 86	90.74 271

NCCC		94.08 143	93.54 165	95.70 77	96.49 192	89.90 87	92.39 214	96.91 181	90.64 153	92.33 281	94.60 269	90.58 168	98.96 118	90.21 176	97.70 252	98.23 151

DPE-MVS		95.89 59	95.88 66	95.92 66	97.93 97	89.83 88	93.46 169	98.30 35	92.37 91	97.75 35	96.95 141	95.14 44	99.51 21	91.74 131	99.28 81	98.41 138
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	92.49 193	91.75 210	94.73 113	96.50 191	89.69 89	92.91 188	97.68 113	78.02 350	92.79 259	94.10 285	90.85 158	97.96 245	84.76 282	98.16 216	96.54 270
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SF-MVS		95.88 60	95.88 66	95.87 70	98.12 80	89.65 90	95.58 88	98.56 17	91.84 114	96.36 101	96.68 162	94.37 75	99.32 71	92.41 114	99.05 107	98.64 115

MSC_two_6792asdad				95.90 67	96.54 187	89.57 91		96.87 184					99.41 42	94.06 55	99.30 73	98.72 100

No_MVS				95.90 67	96.54 187	89.57 91		96.87 184					99.41 42	94.06 55	99.30 73	98.72 100

TEST9					96.45 195	89.46 93	90.60 276	96.92 179	79.09 342	90.49 312	94.39 276	91.31 145	98.88 127

train_agg		92.71 187	91.83 208	95.35 86	96.45 195	89.46 93	90.60 276	96.92 179	79.37 337	90.49 312	94.39 276	91.20 150	98.88 127	88.66 218	98.43 187	97.72 210

OPU-MVS				95.15 100	96.84 164	89.43 95	95.21 104				95.66 224	93.12 101	98.06 232	86.28 262	98.61 169	97.95 180

test_part2					98.21 76	89.41 96				96.72 87

Vis-MVSNet		95.50 74	95.48 84	95.56 81	98.11 81	89.40 97	95.35 96	98.22 46	92.36 92	94.11 207	98.07 46	92.02 127	99.44 32	93.38 84	97.67 254	97.85 195
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
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 46	99.30 73	98.92 75
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CNVR-MVS		94.58 117	94.29 137	95.46 84	96.94 155	89.35 99	91.81 244	96.80 189	89.66 172	93.90 219	95.44 234	92.80 113	98.72 157	92.74 104	98.52 179	98.32 144

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	86.25 242	97.56 42	98.66 21	95.73 19	98.44 197	97.35 4	98.99 115	98.27 149

test_fmvsmconf0.1_n		95.61 70	95.72 76	95.26 92	96.85 163	89.20 101	93.51 167	98.60 16	85.68 256	97.42 52	98.30 38	95.34 35	98.39 198	96.85 8	98.98 116	98.19 155

test_fmvsmconf_n		95.43 77	95.50 83	95.22 97	96.48 194	89.19 102	93.23 177	98.36 29	85.61 259	96.92 77	98.02 51	95.23 41	98.38 201	96.69 11	98.95 125	98.09 163

test_8					96.37 200	89.14 103	90.51 279	96.89 182	79.37 337	90.42 314	94.36 278	91.20 150	98.82 136

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 90	96.90 7	98.62 175	90.30 170	99.60 25	98.72 100

MIMVSNet1		95.52 73	95.45 85	95.72 75	99.14 5	89.02 105	96.23 59	96.87 184	93.73 67	97.87 31	98.49 31	90.73 164	99.05 105	86.43 259	99.60 25	99.10 50

test_vis3_rt		90.40 240	90.03 252	91.52 251	92.58 343	88.95 106	90.38 284	97.72 112	73.30 382	97.79 33	97.51 94	77.05 319	87.10 420	89.03 209	94.89 341	98.50 129

UniMVSNet (Re)		95.32 84	95.15 100	95.80 72	97.79 107	88.91 107	92.91 188	98.07 71	93.46 74	96.31 105	95.97 208	90.14 175	99.34 65	92.11 118	99.64 23	99.16 40

agg_prior					96.20 221	88.89 108		96.88 183		90.21 319			98.78 148

SD-MVS		95.19 93	95.73 75	93.55 171	96.62 181	88.88 109	94.67 123	98.05 75	91.26 138	97.25 61	96.40 177	95.42 30	94.36 382	92.72 106	99.19 93	97.40 234
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.		94.96 101	94.75 116	95.57 80	98.86 22	88.69 110	96.37 46	96.81 188	85.23 266	94.75 192	97.12 128	91.85 131	99.40 49	93.45 78	98.33 199	98.62 119
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
plane_prior7					97.71 114	88.68 111

wuyk23d		87.83 303	90.79 235	78.96 406	90.46 391	88.63 112	92.72 194	90.67 347	91.65 126	98.68 12	97.64 80	96.06 15	77.53 428	59.84 421	99.41 55	70.73 426

mmtdpeth		95.82 62	96.02 58	95.23 95	96.91 158	88.62 113	96.49 39	99.26 4	95.07 44	93.41 230	99.29 4	90.25 173	97.27 299	94.49 45	99.01 114	99.80 3

test_fmvsm_n_1920		94.72 110	94.74 118	94.67 118	96.30 212	88.62 113	93.19 178	98.07 71	85.63 258	97.08 66	97.35 107	90.86 157	97.66 277	95.70 22	98.48 184	97.74 209

DP-MVS		95.62 69	95.84 69	94.97 104	97.16 146	88.62 113	94.54 133	97.64 115	96.94 17	96.58 95	97.32 111	93.07 104	98.72 157	90.45 162	98.84 136	97.57 220

UniMVSNet_NR-MVSNet		95.35 82	95.21 98	95.76 73	97.69 117	88.59 116	92.26 222	97.84 100	94.91 47	96.80 84	95.78 219	90.42 169	99.41 42	91.60 136	99.58 31	99.29 31

DU-MVS		95.28 88	95.12 102	95.75 74	97.75 109	88.59 116	92.58 202	97.81 103	93.99 60	96.80 84	95.90 209	90.10 178	99.41 42	91.60 136	99.58 31	99.26 32

nrg030		96.32 44	96.55 29	95.62 78	97.83 103	88.55 118	95.77 78	98.29 38	92.68 84	98.03 30	97.91 63	95.13 45	98.95 120	93.85 61	99.49 41	99.36 27

PS-MVSNAJss		96.01 54	96.04 56	95.89 69	98.82 25	88.51 119	95.57 89	97.88 95	88.72 192	98.81 7	98.86 12	90.77 160	99.60 10	95.43 31	99.53 37	99.57 16

tt0805		95.42 80	95.93 63	93.86 156	98.75 31	88.47 120	97.68 9	94.29 284	96.48 24	95.38 156	93.63 301	94.89 59	97.94 247	95.38 33	96.92 286	95.17 329

CDPH-MVS		92.67 188	91.83 208	95.18 99	96.94 155	88.46 121	90.70 273	97.07 168	77.38 353	92.34 280	95.08 248	92.67 116	98.88 127	85.74 266	98.57 174	98.20 154

plane_prior3						88.43 122			90.35 162	93.31 235

Fast-Effi-MVS+-dtu		92.77 185	92.16 197	94.58 127	94.66 300	88.25 123	92.05 227	96.65 199	89.62 173	90.08 321	91.23 352	92.56 117	98.60 178	86.30 261	96.27 306	96.90 258

plane_prior6					97.21 144	88.23 124						86.93 223

HQP_MVS		94.26 133	93.93 148	95.23 95	97.71 114	88.12 125	94.56 130	97.81 103	91.74 122	93.31 235	95.59 226	86.93 223	98.95 120	89.26 202	98.51 181	98.60 120

plane_prior						88.12 125	93.01 184		88.98 186						98.06 226

save fliter					97.46 132	88.05 127	92.04 228	97.08 167	87.63 219

UGNet		93.08 172	92.50 191	94.79 111	93.87 319	87.99 128	95.07 111	94.26 286	90.64 153	87.33 370	97.67 77	86.89 225	98.49 190	88.10 226	98.71 158	97.91 186
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	93.73 153	93.44 167	94.60 124	96.14 227	87.90 129	93.36 174	97.14 162	85.53 261	93.90 219	95.45 233	91.30 146	98.59 180	89.51 192	98.62 168	97.31 240
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CSCG		94.69 112	94.75 116	94.52 128	97.55 126	87.87 130	95.01 114	97.57 124	92.68 84	96.20 115	93.44 307	91.92 130	98.78 148	89.11 207	99.24 86	96.92 257

pmmvs-eth3d		91.54 217	90.73 237	93.99 146	95.76 256	87.86 131	90.83 268	93.98 293	78.23 349	94.02 214	96.22 195	82.62 272	96.83 325	86.57 254	98.33 199	97.29 241

pmmvs6		96.80 16	97.36 10	95.15 100	99.12 8	87.82 132	96.68 29	97.86 97	96.10 33	98.14 28	99.28 5	97.94 3	98.21 216	91.38 144	99.69 14	99.42 21

test_fmvsmvis_n_1920		95.08 97	95.40 89	94.13 143	96.66 175	87.75 133	93.44 171	98.49 19	85.57 260	98.27 21	97.11 129	94.11 80	97.75 270	96.26 16	98.72 156	96.89 259

TranMVSNet+NR-MVSNet		96.07 53	96.26 42	95.50 82	98.26 71	87.69 134	93.75 159	97.86 97	95.96 38	97.48 48	97.14 126	95.33 36	99.44 32	90.79 153	99.76 10	99.38 25

EC-MVSNet		95.44 76	95.62 79	94.89 106	96.93 157	87.69 134	96.48 40	99.14 7	93.93 63	92.77 260	94.52 273	93.95 82	99.49 28	93.62 68	99.22 90	97.51 225

fmvsm_l_conf0.5_n_3		95.19 93	95.36 90	94.68 117	96.79 170	87.49 136	93.05 183	98.38 27	87.21 226	96.59 94	97.76 73	94.20 77	98.11 227	95.90 20	98.40 188	98.42 137

alignmvs		93.26 166	92.85 180	94.50 129	95.70 258	87.45 137	93.45 170	95.76 237	91.58 127	95.25 168	92.42 334	81.96 279	98.72 157	91.61 135	97.87 244	97.33 239

UniMVSNet_ETH3D		97.13 9	97.72 4	95.35 86	99.51 2	87.38 138	97.70 8	97.54 126	98.16 3	98.94 3	99.33 3	97.84 4	99.08 100	90.73 155	99.73 13	99.59 15

新几何1				93.17 188	97.16 146	87.29 139		94.43 281	67.95 411	91.29 298	94.94 253	86.97 222	98.23 215	81.06 322	97.75 248	93.98 366

test_fmvs3		92.42 195	92.40 194	92.46 220	93.80 322	87.28 140	93.86 156	97.05 169	76.86 359	96.25 110	98.66 21	82.87 266	91.26 402	95.44 30	96.83 289	98.82 85

test_prior				94.61 121	95.95 242	87.23 141		97.36 144					98.68 168			97.93 183

MM		94.41 125	94.14 144	95.22 97	95.84 248	87.21 142	94.31 139	90.92 344	94.48 53	92.80 258	97.52 90	85.27 245	99.49 28	96.58 13	99.57 33	98.97 65

NR-MVSNet		95.28 88	95.28 96	95.26 92	97.75 109	87.21 142	95.08 110	97.37 139	93.92 65	97.65 37	95.90 209	90.10 178	99.33 70	90.11 179	99.66 21	99.26 32

test_one_0601					98.26 71	87.14 144		98.18 51	94.25 55	96.99 74	97.36 104	95.13 45

NP-MVS					96.82 166	87.10 145					93.40 308

3Dnovator	92.54 3	94.80 108	94.90 108	94.47 132	95.47 272	87.06 146	96.63 31	97.28 153	91.82 117	94.34 204	97.41 98	90.60 167	98.65 173	92.47 113	98.11 221	97.70 211

sasdasda		94.59 115	94.69 120	94.30 137	95.60 266	87.03 147	95.59 85	98.24 42	91.56 128	95.21 171	92.04 341	94.95 55	98.66 170	91.45 141	97.57 259	97.20 245

canonicalmvs		94.59 115	94.69 120	94.30 137	95.60 266	87.03 147	95.59 85	98.24 42	91.56 128	95.21 171	92.04 341	94.95 55	98.66 170	91.45 141	97.57 259	97.20 245

SED-MVS		96.00 55	96.41 36	94.76 112	98.51 49	86.97 149	95.21 104	98.10 65	91.95 105	97.63 38	97.25 115	96.48 10	99.35 62	93.29 86	99.29 76	97.95 180

test_241102_ONE					98.51 49	86.97 149		98.10 65	91.85 111	97.63 38	97.03 136	96.48 10	98.95 120

MVS_111021_HR		93.63 155	93.42 168	94.26 139	96.65 176	86.96 151	89.30 319	96.23 221	88.36 203	93.57 226	94.60 269	93.45 88	97.77 267	90.23 175	98.38 193	98.03 170

DP-MVS Recon		92.31 199	91.88 206	93.60 168	97.18 145	86.87 152	91.10 262	97.37 139	84.92 275	92.08 287	94.08 286	88.59 191	98.20 217	83.50 292	98.14 218	95.73 312

v7n		96.82 13	97.31 11	95.33 88	98.54 46	86.81 153	96.83 22	98.07 71	96.59 23	98.46 18	98.43 35	92.91 109	99.52 20	96.25 17	99.76 10	99.65 11

test_vis1_rt		85.58 336	84.58 339	88.60 328	87.97 412	86.76 154	85.45 387	93.59 297	66.43 414	87.64 365	89.20 380	79.33 296	85.38 424	81.59 314	89.98 407	93.66 374

test12				94.43 134	95.95 242	86.75 155		96.24 220		89.76 330		89.79 184	98.79 145		97.95 239	97.75 208

test_0728_SECOND				94.88 107	98.55 44	86.72 156	95.20 106	98.22 46					99.38 58	93.44 79	99.31 71	98.53 127

DVP-MVS		95.82 62	96.18 46	94.72 114	98.51 49	86.69 157	95.20 106	97.00 172	91.85 111	97.40 54	97.35 107	95.58 24	99.34 65	93.44 79	99.31 71	98.13 161
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	86.69 157	95.34 97	98.18 51	91.85 111	97.63 38	97.37 101	95.58 24

DVP-MVS++		95.93 56	96.34 38	94.70 115	96.54 187	86.66 159	98.45 4	98.22 46	93.26 78	97.54 43	97.36 104	93.12 101	99.38 58	93.88 59	98.68 162	98.04 167

IU-MVS					98.51 49	86.66 159		96.83 187	72.74 387	95.83 132				93.00 98	99.29 76	98.64 115

EG-PatchMatch MVS		94.54 119	94.67 124	94.14 142	97.87 102	86.50 161	92.00 230	96.74 194	88.16 207	96.93 76	97.61 82	93.04 105	97.90 248	91.60 136	98.12 220	98.03 170

MVP-Stereo		90.07 257	88.92 272	93.54 173	96.31 210	86.49 162	90.93 266	95.59 246	79.80 329	91.48 295	95.59 226	80.79 288	97.39 294	78.57 347	91.19 400	96.76 266
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CDS-MVSNet		89.55 266	88.22 291	93.53 174	95.37 277	86.49 162	89.26 320	93.59 297	79.76 331	91.15 302	92.31 335	77.12 318	98.38 201	77.51 354	97.92 241	95.71 313
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS-MVSNet		94.49 121	94.35 136	94.92 105	98.25 73	86.46 164	97.13 17	94.31 283	96.24 31	96.28 109	96.36 184	82.88 265	99.35 62	88.19 223	99.52 39	98.96 67

WR-MVS_H		96.60 29	97.05 17	95.24 94	99.02 12	86.44 165	96.78 26	98.08 68	97.42 10	98.48 17	97.86 66	91.76 136	99.63 8	94.23 52	99.84 3	99.66 9

PMMVS		83.00 360	81.11 369	88.66 327	83.81 430	86.44 165	82.24 411	85.65 385	61.75 424	82.07 409	85.64 407	79.75 293	91.59 401	75.99 367	93.09 383	87.94 414

TAMVS		90.16 251	89.05 268	93.49 178	96.49 192	86.37 167	90.34 286	92.55 320	80.84 324	92.99 251	94.57 272	81.94 280	98.20 217	73.51 382	98.21 212	95.90 306

AdaColmap		91.63 214	91.36 219	92.47 219	95.56 268	86.36 168	92.24 224	96.27 218	88.88 190	89.90 326	92.69 326	91.65 137	98.32 207	77.38 356	97.64 256	92.72 391

Anonymous20231211		96.60 29	97.13 16	95.00 103	97.46 132	86.35 169	97.11 18	98.24 42	97.58 9	98.72 9	98.97 9	93.15 100	99.15 91	93.18 91	99.74 12	99.50 19

ETV-MVS		92.99 175	92.74 183	93.72 164	95.86 247	86.30 170	92.33 216	97.84 100	91.70 125	92.81 257	86.17 403	92.22 123	99.19 88	88.03 230	97.73 249	95.66 317

fmvsm_l_conf0.5_n		93.79 151	93.81 150	93.73 163	96.16 224	86.26 171	92.46 208	96.72 195	81.69 315	95.77 134	97.11 129	90.83 159	97.82 259	95.58 25	97.99 235	97.11 248

API-MVS		91.52 218	91.61 211	91.26 261	94.16 309	86.26 171	94.66 124	94.82 271	91.17 141	92.13 286	91.08 355	90.03 181	97.06 314	79.09 344	97.35 270	90.45 407

EPNet		89.80 265	88.25 288	94.45 133	83.91 429	86.18 173	93.87 155	87.07 374	91.16 142	80.64 417	94.72 263	78.83 299	98.89 126	85.17 271	98.89 129	98.28 148
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
JIA-IIPM		85.08 340	83.04 355	91.19 266	87.56 414	86.14 174	89.40 316	84.44 400	88.98 186	82.20 408	97.95 56	56.82 405	96.15 345	76.55 363	83.45 420	91.30 402

test_f		86.65 330	87.13 311	85.19 377	90.28 393	86.11 175	86.52 374	91.66 337	69.76 405	95.73 140	97.21 121	69.51 355	81.28 427	89.15 206	94.40 352	88.17 413

VDD-MVS		94.37 127	94.37 134	94.40 135	97.49 129	86.07 176	93.97 153	93.28 304	94.49 52	96.24 111	97.78 68	87.99 204	98.79 145	88.92 211	99.14 100	98.34 143

MVS_0304		92.88 179	92.27 195	94.69 116	92.35 349	86.03 177	92.88 190	89.68 351	90.53 156	91.52 294	96.43 174	82.52 273	99.32 71	95.01 38	99.54 36	98.71 103

EI-MVSNet-Vis-set		94.36 128	94.28 138	94.61 121	92.55 345	85.98 178	92.44 210	94.69 277	93.70 68	96.12 120	95.81 215	91.24 147	98.86 131	93.76 66	98.22 211	98.98 63

mvsany_test1		83.91 353	82.93 357	86.84 358	86.18 422	85.93 179	81.11 414	75.03 428	70.80 400	88.57 352	94.63 267	83.08 263	87.38 419	80.39 324	86.57 415	87.21 415

Anonymous20240529		95.50 74	95.83 70	94.50 129	97.33 138	85.93 179	95.19 108	96.77 192	96.64 21	97.61 41	98.05 47	93.23 97	98.79 145	88.60 219	99.04 112	98.78 91

EI-MVSNet-UG-set		94.35 129	94.27 140	94.59 125	92.46 348	85.87 181	92.42 212	94.69 277	93.67 71	96.13 119	95.84 213	91.20 150	98.86 131	93.78 63	98.23 209	99.03 55

PCF-MVS	84.52 17	89.12 275	87.71 299	93.34 181	96.06 233	85.84 182	86.58 373	97.31 148	68.46 410	93.61 225	93.89 295	87.51 211	98.52 188	67.85 407	98.11 221	95.66 317
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_0402		95.73 66	96.22 44	94.26 139	98.19 77	85.77 183	93.24 176	97.24 156	96.88 18	97.69 36	97.77 72	94.12 79	99.13 95	91.54 140	99.29 76	97.88 190

fmvsm_s_conf0.5_n_a		94.02 145	94.08 147	93.84 157	96.72 172	85.73 184	93.65 165	95.23 260	83.30 291	95.13 174	97.56 85	92.22 123	97.17 306	95.51 28	97.41 267	98.64 115

fmvsm_s_conf0.1_n_a		94.26 133	94.37 134	93.95 151	97.36 136	85.72 185	94.15 144	95.44 252	83.25 293	95.51 148	98.05 47	92.54 118	97.19 305	95.55 27	97.46 265	98.94 69

MCST-MVS		92.91 177	92.51 190	94.10 144	97.52 127	85.72 185	91.36 256	97.13 164	80.33 326	92.91 256	94.24 280	91.23 148	98.72 157	89.99 183	97.93 240	97.86 193

fmvsm_l_conf0.5_n_a		93.59 156	93.63 159	93.49 178	96.10 230	85.66 187	92.32 217	96.57 204	81.32 318	95.63 143	97.14 126	90.19 174	97.73 273	95.37 34	98.03 229	97.07 249

pmmvs4		88.95 283	87.70 300	92.70 205	94.30 307	85.60 188	87.22 355	92.16 328	74.62 373	89.75 331	94.19 282	77.97 309	96.41 338	82.71 299	96.36 303	96.09 295

EPP-MVSNet		93.91 149	93.68 158	94.59 125	98.08 83	85.55 189	97.44 11	94.03 289	94.22 57	94.94 184	96.19 196	82.07 277	99.57 15	87.28 243	98.89 129	98.65 110

MGCFI-Net		94.44 123	94.67 124	93.75 161	95.56 268	85.47 190	95.25 103	98.24 42	91.53 130	95.04 180	92.21 336	94.94 57	98.54 186	91.56 139	97.66 255	97.24 243

test_fmvs2		90.62 235	90.40 245	91.29 259	91.93 365	85.46 191	92.70 196	96.48 211	74.44 374	94.91 186	97.59 83	75.52 331	90.57 405	93.44 79	96.56 298	97.84 196

CMPMVS	68.83 22	87.28 317	85.67 333	92.09 231	88.77 409	85.42 192	90.31 287	94.38 282	70.02 404	88.00 359	93.30 310	73.78 338	94.03 387	75.96 368	96.54 299	96.83 262
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ACMH	88.36 12	96.59 31	97.43 6	94.07 145	98.56 41	85.33 193	96.33 49	98.30 35	94.66 49	98.72 9	98.30 38	97.51 5	98.00 241	94.87 40	99.59 27	98.86 81
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test222					96.95 154	85.27 194	88.83 330	93.61 296	65.09 419	90.74 308	94.85 256	84.62 252			97.36 269	93.91 367

GeoE		94.55 118	94.68 123	94.15 141	97.23 141	85.11 195	94.14 146	97.34 146	88.71 193	95.26 166	95.50 231	94.65 65	99.12 96	90.94 151	98.40 188	98.23 151

pm-mvs1		95.43 77	95.94 61	93.93 152	98.38 61	85.08 196	95.46 94	97.12 165	91.84 114	97.28 59	98.46 33	95.30 38	97.71 274	90.17 177	99.42 51	98.99 59

fmvsm_s_conf0.5_n_5		94.50 120	94.80 112	93.60 168	96.80 168	84.93 197	92.81 191	97.59 122	85.27 265	96.85 82	97.29 112	91.48 142	98.05 233	96.67 12	98.47 185	97.83 197

HQP5-MVS						84.89 198

HQP-MVS		92.09 205	91.49 216	93.88 154	96.36 202	84.89 198	91.37 253	97.31 148	87.16 227	88.81 343	93.40 308	84.76 250	98.60 178	86.55 256	97.73 249	98.14 160

DTE-MVSNet		96.74 21	97.43 6	94.67 118	99.13 6	84.68 200	96.51 36	97.94 94	98.14 4	98.67 13	98.32 37	95.04 50	99.69 4	93.27 88	99.82 7	99.62 13

PEN-MVS		96.69 24	97.39 9	94.61 121	99.16 4	84.50 201	96.54 34	98.05 75	98.06 5	98.64 14	98.25 40	95.01 53	99.65 5	92.95 100	99.83 5	99.68 7

fmvsm_s_conf0.1_n		94.19 141	94.41 131	93.52 176	97.22 143	84.37 202	93.73 160	95.26 259	84.45 281	95.76 135	98.00 52	91.85 131	97.21 302	95.62 23	97.82 246	98.98 63

fmvsm_s_conf0.5_n		94.00 146	94.20 142	93.42 180	96.69 173	84.37 202	93.38 173	95.13 262	84.50 280	95.40 155	97.55 89	91.77 134	97.20 303	95.59 24	97.79 247	98.69 107

GBi-Net		93.21 169	92.96 176	93.97 148	95.40 274	84.29 204	95.99 67	96.56 205	88.63 194	95.10 176	98.53 28	81.31 284	98.98 113	86.74 249	98.38 193	98.65 110

test1		93.21 169	92.96 176	93.97 148	95.40 274	84.29 204	95.99 67	96.56 205	88.63 194	95.10 176	98.53 28	81.31 284	98.98 113	86.74 249	98.38 193	98.65 110

FMVSNet1		94.84 105	95.13 101	93.97 148	97.60 122	84.29 204	95.99 67	96.56 205	92.38 90	97.03 71	98.53 28	90.12 176	98.98 113	88.78 215	99.16 98	98.65 110

原ACMM1				92.87 200	96.91 158	84.22 207		97.01 171	76.84 360	89.64 332	94.46 274	88.00 203	98.70 164	81.53 316	98.01 232	95.70 315

DPM-MVS		89.35 271	88.40 281	92.18 228	96.13 229	84.20 208	86.96 360	96.15 227	75.40 368	87.36 369	91.55 350	83.30 260	98.01 239	82.17 309	96.62 297	94.32 359

旧先验1					96.20 221	84.17 209		94.82 271			95.57 230	89.57 185			97.89 242	96.32 283

OpenMVS	89.45 8	92.27 202	92.13 200	92.68 207	94.53 303	84.10 210	95.70 80	97.03 170	82.44 307	91.14 303	96.42 175	88.47 193	98.38 201	85.95 264	97.47 264	95.55 322

PS-CasMVS		96.69 24	97.43 6	94.49 131	99.13 6	84.09 211	96.61 32	97.97 88	97.91 6	98.64 14	98.13 43	95.24 40	99.65 5	93.39 83	99.84 3	99.72 4

EIA-MVS		92.35 198	92.03 201	93.30 184	95.81 252	83.97 212	92.80 193	98.17 55	87.71 216	89.79 329	87.56 393	91.17 153	99.18 89	87.97 231	97.27 271	96.77 265

PVSNet_Blended_VisFu		91.63 214	91.20 222	92.94 196	97.73 112	83.95 213	92.14 225	97.46 134	78.85 346	92.35 278	94.98 251	84.16 254	99.08 100	86.36 260	96.77 292	95.79 310

CP-MVSNet		96.19 49	96.80 20	94.38 136	98.99 16	83.82 214	96.31 52	97.53 128	97.60 8	98.34 20	97.52 90	91.98 129	99.63 8	93.08 96	99.81 8	99.70 5

lessismore_v0				93.87 155	98.05 86	83.77 215		80.32 418		97.13 65	97.91 63	77.49 312	99.11 98	92.62 108	98.08 225	98.74 98

GDP-MVS		91.56 216	90.83 233	93.77 160	96.34 206	83.65 216	93.66 164	98.12 61	87.32 224	92.98 253	94.71 264	63.58 387	99.30 73	92.61 109	98.14 218	98.35 142

CLD-MVS		91.82 208	91.41 218	93.04 190	96.37 200	83.65 216	86.82 365	97.29 151	84.65 279	92.27 282	89.67 374	92.20 125	97.85 258	83.95 290	99.47 42	97.62 216
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CANet		92.38 197	91.99 203	93.52 176	93.82 321	83.46 218	91.14 260	97.00 172	89.81 169	86.47 374	94.04 287	87.90 206	99.21 84	89.50 193	98.27 204	97.90 187

BP-MVS1		91.77 210	91.10 226	93.75 161	96.42 197	83.40 219	94.10 148	91.89 334	91.27 137	93.36 234	94.85 256	64.43 381	99.29 74	94.88 39	98.74 155	98.56 124

QAPM		92.88 179	92.77 181	93.22 186	95.82 250	83.31 220	96.45 41	97.35 145	83.91 286	93.75 221	96.77 152	89.25 188	98.88 127	84.56 284	97.02 280	97.49 226

Effi-MVS+		92.79 183	92.74 183	92.94 196	95.10 282	83.30 221	94.00 151	97.53 128	91.36 136	89.35 336	90.65 365	94.01 81	98.66 170	87.40 241	95.30 331	96.88 261

sd_testset		93.94 148	94.39 132	92.61 213	97.93 97	83.24 222	93.17 179	95.04 264	93.65 72	95.51 148	98.63 23	94.49 72	95.89 354	81.72 313	99.35 60	98.70 104

casdiffmvs_mvg		95.10 96	95.62 79	93.53 174	96.25 218	83.23 223	92.66 198	98.19 49	93.06 81	97.49 47	97.15 125	94.78 61	98.71 163	92.27 116	98.72 156	98.65 110
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		92.58 190	92.50 191	92.83 202	96.55 186	83.22 224	92.43 211	91.64 338	94.10 59	95.59 145	96.64 164	81.88 281	97.50 284	85.12 275	98.52 179	97.77 205

SixPastTwentyTwo		94.91 102	95.21 98	93.98 147	98.52 48	83.19 225	95.93 71	94.84 270	94.86 48	98.49 16	98.74 18	81.45 282	99.60 10	94.69 42	99.39 57	99.15 41

VPA-MVSNet		95.14 95	95.67 78	93.58 170	97.76 108	83.15 226	94.58 128	97.58 123	93.39 75	97.05 70	98.04 49	93.25 96	98.51 189	89.75 189	99.59 27	99.08 51

LCM-MVSNet-Re		94.20 139	94.58 128	93.04 190	95.91 244	83.13 227	93.79 158	99.19 6	92.00 104	98.84 6	98.04 49	93.64 84	99.02 110	81.28 318	98.54 177	96.96 256

mvs5depth		95.28 88	95.82 72	93.66 165	96.42 197	83.08 228	97.35 12	99.28 3	96.44 26	96.20 115	99.65 2	84.10 255	98.01 239	94.06 55	98.93 126	99.87 1

MSDG		90.82 227	90.67 238	91.26 261	94.16 309	83.08 228	86.63 370	96.19 224	90.60 155	91.94 289	91.89 343	89.16 189	95.75 356	80.96 323	94.51 351	94.95 340

ambc				92.98 192	96.88 160	83.01 230	95.92 72	96.38 215		96.41 99	97.48 96	88.26 197	97.80 262	89.96 184	98.93 126	98.12 162

dmvs_re		84.69 345	83.94 348	86.95 355	92.24 352	82.93 231	89.51 311	87.37 370	84.38 283	85.37 379	85.08 411	72.44 342	86.59 421	68.05 406	91.03 403	91.33 401

SDMVSNet		94.43 124	95.02 105	92.69 206	97.93 97	82.88 232	91.92 236	95.99 233	93.65 72	95.51 148	98.63 23	94.60 67	96.48 335	87.57 237	99.35 60	98.70 104

MSLP-MVS++		93.25 168	93.88 149	91.37 254	96.34 206	82.81 233	93.11 181	97.74 110	89.37 178	94.08 209	95.29 241	90.40 171	96.35 342	90.35 167	98.25 207	94.96 339

fmvsm_s_conf0.5_n_4		94.26 133	94.58 128	93.31 182	96.40 199	82.73 234	92.59 201	97.41 137	86.60 236	96.33 102	97.07 132	89.91 182	98.07 231	96.88 7	98.01 232	99.13 43

K. test v3		93.37 162	93.27 172	93.66 165	98.05 86	82.62 235	94.35 136	86.62 376	96.05 35	97.51 46	98.85 14	76.59 327	99.65 5	93.21 90	98.20 214	98.73 99

test_fmvs1_n		88.73 289	88.38 282	89.76 306	92.06 360	82.53 236	92.30 220	96.59 203	71.14 395	92.58 266	95.41 238	68.55 357	89.57 413	91.12 146	95.66 319	97.18 247

Fast-Effi-MVS+		91.28 224	90.86 231	92.53 217	95.45 273	82.53 236	89.25 322	96.52 209	85.00 273	89.91 325	88.55 386	92.94 107	98.84 134	84.72 283	95.44 326	96.22 290

test_vis1_n		89.01 280	89.01 270	89.03 319	92.57 344	82.46 238	92.62 200	96.06 228	73.02 385	90.40 315	95.77 220	74.86 333	89.68 411	90.78 154	94.98 339	94.95 340

VDDNet		94.03 144	94.27 140	93.31 182	98.87 21	82.36 239	95.51 93	91.78 336	97.19 13	96.32 104	98.60 25	84.24 253	98.75 152	87.09 246	98.83 141	98.81 87

mvsmamba		90.24 249	89.43 263	92.64 208	95.52 270	82.36 239	96.64 30	92.29 324	81.77 313	92.14 285	96.28 190	70.59 351	99.10 99	84.44 286	95.22 334	96.47 277

114514_t		90.51 236	89.80 257	92.63 211	98.00 92	82.24 241	93.40 172	97.29 151	65.84 417	89.40 335	94.80 260	86.99 221	98.75 152	83.88 291	98.61 169	96.89 259

fmvsm_s_conf0.5_n_3		95.20 92	95.95 60	92.94 196	96.60 182	82.18 242	93.13 180	98.39 26	91.44 133	97.16 63	97.68 75	93.03 106	97.82 259	97.54 3	98.63 167	98.81 87

testdata				91.03 269	96.87 161	82.01 243		94.28 285	71.55 392	92.46 270	95.42 235	85.65 241	97.38 296	82.64 300	97.27 271	93.70 373

FMVSNet2		92.78 184	92.73 185	92.95 195	95.40 274	81.98 244	94.18 143	95.53 250	88.63 194	96.05 122	97.37 101	81.31 284	98.81 141	87.38 242	98.67 164	98.06 164

TransMVSNet (Re)		95.27 91	96.04 56	92.97 193	98.37 63	81.92 245	95.07 111	96.76 193	93.97 62	97.77 34	98.57 26	95.72 20	97.90 248	88.89 213	99.23 87	99.08 51

FC-MVSNet-test		95.32 84	95.88 66	93.62 167	98.49 56	81.77 246	95.90 73	98.32 32	93.93 63	97.53 45	97.56 85	88.48 192	99.40 49	92.91 101	99.83 5	99.68 7

FIs		94.90 103	95.35 91	93.55 171	98.28 69	81.76 247	95.33 98	98.14 59	93.05 82	97.07 67	97.18 123	87.65 208	99.29 74	91.72 132	99.69 14	99.61 14

fmvsm_s_conf0.5_n_2		94.25 137	94.63 126	93.10 189	96.65 176	81.75 248	91.72 247	97.25 154	86.93 235	97.20 62	97.67 77	88.44 194	98.14 226	97.06 6	98.77 150	99.42 21

fmvsm_s_conf0.1_n_2		94.38 126	94.78 115	93.19 187	97.07 150	81.72 249	91.97 231	97.51 131	87.05 231	97.31 56	97.92 61	88.29 196	98.15 223	97.10 5	98.81 144	99.70 5

ab-mvs		92.40 196	92.62 188	91.74 240	97.02 151	81.65 250	95.84 76	95.50 251	86.95 233	92.95 255	97.56 85	90.70 165	97.50 284	79.63 337	97.43 266	96.06 297

xiu_mvs_v1_base_debu		91.47 219	91.52 213	91.33 256	95.69 259	81.56 251	89.92 299	96.05 230	83.22 294	91.26 299	90.74 360	91.55 139	98.82 136	89.29 199	95.91 312	93.62 376

xiu_mvs_v1_base		91.47 219	91.52 213	91.33 256	95.69 259	81.56 251	89.92 299	96.05 230	83.22 294	91.26 299	90.74 360	91.55 139	98.82 136	89.29 199	95.91 312	93.62 376

xiu_mvs_v1_base_debi		91.47 219	91.52 213	91.33 256	95.69 259	81.56 251	89.92 299	96.05 230	83.22 294	91.26 299	90.74 360	91.55 139	98.82 136	89.29 199	95.91 312	93.62 376

casdiffmvs		94.32 131	94.80 112	92.85 201	96.05 234	81.44 254	92.35 215	98.05 75	91.53 130	95.75 137	96.80 151	93.35 93	98.49 190	91.01 150	98.32 201	98.64 115
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		86.15 332	84.27 343	91.79 238	93.04 334	81.28 255	87.17 357	86.14 379	79.57 334	83.65 396	88.66 383	57.10 403	98.18 220	87.74 235	95.40 327	95.90 306

test_fmvs1		87.59 310	87.27 306	88.54 329	88.32 411	81.26 256	90.43 283	95.72 239	70.55 401	91.70 292	94.63 267	68.13 358	89.42 415	90.59 158	95.34 330	94.94 342

V42		93.43 161	93.58 162	92.97 193	95.34 278	81.22 257	92.67 197	96.49 210	87.25 225	96.20 115	96.37 183	87.32 214	98.85 133	92.39 115	98.21 212	98.85 84

OpenMVS_ROB	85.12 16	89.52 268	89.05 268	90.92 274	94.58 302	81.21 258	91.10 262	93.41 303	77.03 358	93.41 230	93.99 291	83.23 261	97.80 262	79.93 334	94.80 345	93.74 372

PAPM_NR		91.03 226	90.81 234	91.68 244	96.73 171	81.10 259	93.72 161	96.35 216	88.19 205	88.77 347	92.12 340	85.09 248	97.25 300	82.40 306	93.90 366	96.68 268

baseline		94.26 133	94.80 112	92.64 208	96.08 232	80.99 260	93.69 162	98.04 79	90.80 149	94.89 187	96.32 186	93.19 98	98.48 194	91.68 134	98.51 181	98.43 136

1112_ss		88.42 294	87.41 303	91.45 252	96.69 173	80.99 260	89.72 306	96.72 195	73.37 381	87.00 372	90.69 363	77.38 315	98.20 217	81.38 317	93.72 369	95.15 331

tfpnnormal		94.27 132	94.87 110	92.48 218	97.71 114	80.88 262	94.55 132	95.41 255	93.70 68	96.67 90	97.72 74	91.40 143	98.18 220	87.45 239	99.18 95	98.36 139

Baseline_NR-MVSNet		94.47 122	95.09 104	92.60 214	98.50 55	80.82 263	92.08 226	96.68 197	93.82 66	96.29 107	98.56 27	90.10 178	97.75 270	90.10 181	99.66 21	99.24 34

HyFIR lowres test		87.19 321	85.51 334	92.24 223	97.12 149	80.51 264	85.03 390	96.06 228	66.11 416	91.66 293	92.98 319	70.12 353	99.14 93	75.29 371	95.23 333	97.07 249

UnsupCasMVSNet_eth		90.33 246	90.34 246	90.28 292	94.64 301	80.24 265	89.69 307	95.88 234	85.77 253	93.94 218	95.69 223	81.99 278	92.98 395	84.21 288	91.30 399	97.62 216

MDA-MVSNet-bldmvs		91.04 225	90.88 230	91.55 249	94.68 299	80.16 266	85.49 386	92.14 329	90.41 161	94.93 185	95.79 216	85.10 247	96.93 320	85.15 273	94.19 361	97.57 220

v10		94.68 113	95.27 97	92.90 199	96.57 184	80.15 267	94.65 125	97.57 124	90.68 152	97.43 50	98.00 52	88.18 198	99.15 91	94.84 41	99.55 35	99.41 23

VNet		92.67 188	92.96 176	91.79 238	96.27 215	80.15 267	91.95 232	94.98 266	92.19 100	94.52 199	96.07 203	87.43 212	97.39 294	84.83 280	98.38 193	97.83 197

DELS-MVS		92.05 206	92.16 197	91.72 241	94.44 304	80.13 269	87.62 346	97.25 154	87.34 223	92.22 283	93.18 315	89.54 186	98.73 156	89.67 190	98.20 214	96.30 284
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		89.17 274	88.32 283	91.70 243	95.73 257	80.07 270	88.10 341	93.22 305	71.98 390	90.09 320	92.79 323	78.53 304	98.56 183	87.43 240	97.06 278	96.46 278
jason: jason.
MVSFormer		92.18 204	92.23 196	92.04 233	94.74 295	80.06 271	97.15 15	97.37 139	88.98 186	88.83 341	92.79 323	77.02 320	99.60 10	96.41 14	96.75 293	96.46 278

lupinMVS		88.34 296	87.31 304	91.45 252	94.74 295	80.06 271	87.23 354	92.27 325	71.10 396	88.83 341	91.15 353	77.02 320	98.53 187	86.67 252	96.75 293	95.76 311

WR-MVS		93.49 158	93.72 155	92.80 203	97.57 125	80.03 273	90.14 292	95.68 240	93.70 68	96.62 92	95.39 239	87.21 216	99.04 108	87.50 238	99.64 23	99.33 28

CANet_DTU		89.85 263	89.17 266	91.87 235	92.20 355	80.02 274	90.79 269	95.87 235	86.02 248	82.53 407	91.77 345	80.01 292	98.57 182	85.66 268	97.70 252	97.01 254

FA-MVS(test-final)		91.81 209	91.85 207	91.68 244	94.95 285	79.99 275	96.00 66	93.44 302	87.80 213	94.02 214	97.29 112	77.60 311	98.45 196	88.04 229	97.49 262	96.61 269

Patchmatch-RL test		88.81 286	88.52 278	89.69 309	95.33 279	79.94 276	86.22 378	92.71 315	78.46 347	95.80 133	94.18 283	66.25 371	95.33 367	89.22 204	98.53 178	93.78 370

FMVSNet3		90.78 229	90.32 247	92.16 229	93.03 335	79.92 277	92.54 203	94.95 267	86.17 246	95.10 176	96.01 206	69.97 354	98.75 152	86.74 249	98.38 193	97.82 200

XXY-MVS		92.58 190	93.16 174	90.84 278	97.75 109	79.84 278	91.87 240	96.22 223	85.94 249	95.53 147	97.68 75	92.69 115	94.48 378	83.21 295	97.51 261	98.21 153

test_yl		90.11 254	89.73 260	91.26 261	94.09 312	79.82 279	90.44 280	92.65 316	90.90 144	93.19 245	93.30 310	73.90 336	98.03 235	82.23 307	96.87 287	95.93 303

DCV-MVSNet		90.11 254	89.73 260	91.26 261	94.09 312	79.82 279	90.44 280	92.65 316	90.90 144	93.19 245	93.30 310	73.90 336	98.03 235	82.23 307	96.87 287	95.93 303

FMVSNet5		87.82 304	86.56 323	91.62 246	92.31 350	79.81 281	93.49 168	94.81 273	83.26 292	91.36 297	96.93 143	52.77 412	97.49 286	76.07 366	98.03 229	97.55 223

v8		94.65 114	95.29 95	92.74 204	96.65 176	79.77 282	94.59 126	97.17 160	91.86 110	97.47 49	97.93 57	88.16 199	99.08 100	94.32 49	99.47 42	99.38 25

tttt0517		89.81 264	88.90 274	92.55 216	97.00 152	79.73 283	95.03 113	83.65 402	89.88 168	95.30 162	94.79 261	53.64 410	99.39 52	91.99 123	98.79 148	98.54 125

v1192		93.49 158	93.78 153	92.62 212	96.16 224	79.62 284	91.83 243	97.22 158	86.07 247	96.10 121	96.38 182	87.22 215	99.02 110	94.14 54	98.88 131	99.22 35

v1144		93.50 157	93.81 150	92.57 215	96.28 213	79.61 285	91.86 242	96.96 175	86.95 233	95.91 128	96.32 186	87.65 208	98.96 118	93.51 72	98.88 131	99.13 43

FE-MVS		89.06 277	88.29 285	91.36 255	94.78 292	79.57 286	96.77 27	90.99 342	84.87 276	92.96 254	96.29 188	60.69 399	98.80 144	80.18 329	97.11 277	95.71 313

BH-untuned		90.68 232	90.90 229	90.05 302	95.98 240	79.57 286	90.04 295	94.94 268	87.91 209	94.07 210	93.00 317	87.76 207	97.78 266	79.19 343	95.17 335	92.80 390

KD-MVS_self_test		94.10 142	94.73 119	92.19 225	97.66 120	79.49 288	94.86 118	97.12 165	89.59 174	96.87 78	97.65 79	90.40 171	98.34 206	89.08 208	99.35 60	98.75 95

CHOSEN 1792x2688		87.19 321	85.92 332	91.00 272	97.13 148	79.41 289	84.51 397	95.60 242	64.14 420	90.07 322	94.81 258	78.26 307	97.14 309	73.34 383	95.38 329	96.46 278

thisisatest0530		88.69 290	87.52 302	92.20 224	96.33 208	79.36 290	92.81 191	84.01 401	86.44 238	93.67 224	92.68 327	53.62 411	99.25 81	89.65 191	98.45 186	98.00 172

LFMVS		91.33 222	91.16 225	91.82 237	96.27 215	79.36 290	95.01 114	85.61 389	96.04 36	94.82 189	97.06 134	72.03 346	98.46 195	84.96 279	98.70 160	97.65 215

TR-MVS		87.70 305	87.17 309	89.27 316	94.11 311	79.26 292	88.69 334	91.86 335	81.94 312	90.69 310	89.79 371	82.82 268	97.42 291	72.65 388	91.98 396	91.14 403

test20.03		90.80 228	90.85 232	90.63 284	95.63 264	79.24 293	89.81 303	92.87 310	89.90 167	94.39 201	96.40 177	85.77 238	95.27 369	73.86 381	99.05 107	97.39 235

IterMVS-SCA-FT		91.65 213	91.55 212	91.94 234	93.89 318	79.22 294	87.56 349	93.51 300	91.53 130	95.37 158	96.62 165	78.65 301	98.90 124	91.89 127	94.95 340	97.70 211

EI-MVSNet		92.99 175	93.26 173	92.19 225	92.12 358	79.21 295	92.32 217	94.67 279	91.77 120	95.24 169	95.85 211	87.14 218	98.49 190	91.99 123	98.26 205	98.86 81

IterMVS-LS		93.78 152	94.28 138	92.27 222	96.27 215	79.21 295	91.87 240	96.78 190	91.77 120	96.57 96	97.07 132	87.15 217	98.74 155	91.99 123	99.03 113	98.86 81
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CR-MVSNet		87.89 301	87.12 312	90.22 295	91.01 381	78.93 297	92.52 204	92.81 311	73.08 384	89.10 337	96.93 143	67.11 363	97.64 279	88.80 214	92.70 388	94.08 361

RPMNet		90.31 248	90.14 251	90.81 280	91.01 381	78.93 297	92.52 204	98.12 61	91.91 108	89.10 337	96.89 146	68.84 356	99.41 42	90.17 177	92.70 388	94.08 361

test_cas_vis1_n_1920		88.25 297	88.27 287	88.20 337	92.19 356	78.92 299	89.45 313	95.44 252	75.29 371	93.23 243	95.65 225	71.58 347	90.23 409	88.05 228	93.55 373	95.44 325

patch_mono-2		92.46 194	92.72 186	91.71 242	96.65 176	78.91 300	88.85 329	97.17 160	83.89 287	92.45 271	96.76 154	89.86 183	97.09 311	90.24 174	98.59 172	99.12 46

MVSMamba_PlusPlus		94.82 107	95.89 65	91.62 246	97.82 104	78.88 301	96.52 35	97.60 121	97.14 14	94.23 205	98.48 32	87.01 220	99.71 3	95.43 31	98.80 146	96.28 286

UnsupCasMVSNet_bld		88.50 292	88.03 295	89.90 304	95.52 270	78.88 301	87.39 353	94.02 291	79.32 340	93.06 248	94.02 289	80.72 289	94.27 383	75.16 372	93.08 384	96.54 270

v2v482		93.29 164	93.63 159	92.29 221	96.35 205	78.82 303	91.77 246	96.28 217	88.45 199	95.70 142	96.26 193	86.02 237	98.90 124	93.02 97	98.81 144	99.14 42

Anonymous20231206		88.77 287	88.29 285	90.20 297	96.31 210	78.81 304	89.56 310	93.49 301	74.26 377	92.38 275	95.58 229	82.21 274	95.43 364	72.07 390	98.75 154	96.34 282

PVSNet_BlendedMVS		90.35 245	89.96 253	91.54 250	94.81 290	78.80 305	90.14 292	96.93 177	79.43 336	88.68 350	95.06 249	86.27 234	98.15 223	80.27 326	98.04 228	97.68 213

PVSNet_Blended		88.74 288	88.16 294	90.46 289	94.81 290	78.80 305	86.64 369	96.93 177	74.67 372	88.68 350	89.18 381	86.27 234	98.15 223	80.27 326	96.00 310	94.44 356

BH-RMVSNet		90.47 238	90.44 243	90.56 286	95.21 281	78.65 307	89.15 323	93.94 294	88.21 204	92.74 261	94.22 281	86.38 231	97.88 252	78.67 346	95.39 328	95.14 332

balanced_conf03		93.45 160	94.17 143	91.28 260	95.81 252	78.40 308	96.20 60	97.48 133	88.56 198	95.29 164	97.20 122	85.56 244	99.21 84	92.52 112	98.91 128	96.24 289

D2MVS		89.93 260	89.60 262	90.92 274	94.03 315	78.40 308	88.69 334	94.85 269	78.96 344	93.08 247	95.09 247	74.57 334	96.94 318	88.19 223	98.96 123	97.41 231

v1921920		93.26 166	93.61 161	92.19 225	96.04 238	78.31 310	91.88 239	97.24 156	85.17 268	96.19 118	96.19 196	86.76 227	99.05 105	94.18 53	98.84 136	99.22 35

v144192		93.20 171	93.54 165	92.16 229	96.05 234	78.26 311	91.95 232	97.14 162	84.98 274	95.96 124	96.11 201	87.08 219	99.04 108	93.79 62	98.84 136	99.17 39

diffmvs		91.74 211	91.93 205	91.15 267	93.06 333	78.17 312	88.77 332	97.51 131	86.28 241	92.42 273	93.96 292	88.04 202	97.46 287	90.69 157	96.67 296	97.82 200
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		87.23 318	86.82 317	88.46 333	93.96 316	77.94 313	86.84 363	92.78 314	77.59 352	87.61 367	91.83 344	78.75 300	91.92 399	77.84 350	94.20 359	95.52 324

MS-PatchMatch		88.05 300	87.75 298	88.95 320	93.28 328	77.93 314	87.88 344	92.49 321	75.42 367	92.57 267	93.59 304	80.44 290	94.24 385	81.28 318	92.75 387	94.69 352

HY-MVS	82.50 18	86.81 329	85.93 331	89.47 310	93.63 323	77.93 314	94.02 150	91.58 339	75.68 364	83.64 397	93.64 300	77.40 314	97.42 291	71.70 393	92.07 395	93.05 385

v1240		93.29 164	93.71 156	92.06 232	96.01 239	77.89 316	91.81 244	97.37 139	85.12 270	96.69 89	96.40 177	86.67 228	99.07 104	94.51 44	98.76 152	99.22 35

CL-MVSNet_self_test		90.04 259	89.90 255	90.47 287	95.24 280	77.81 317	86.60 372	92.62 318	85.64 257	93.25 242	93.92 293	83.84 256	96.06 349	79.93 334	98.03 229	97.53 224

Test_1112_low_res		87.50 313	86.58 321	90.25 294	96.80 168	77.75 318	87.53 351	96.25 219	69.73 406	86.47 374	93.61 303	75.67 330	97.88 252	79.95 332	93.20 379	95.11 335

v148		92.87 181	93.29 169	91.62 246	96.25 218	77.72 319	91.28 257	95.05 263	89.69 171	95.93 127	96.04 204	87.34 213	98.38 201	90.05 182	97.99 235	98.78 91

MVS		84.98 341	84.30 342	87.01 352	91.03 380	77.69 320	91.94 234	94.16 287	59.36 425	84.23 392	87.50 395	85.66 240	96.80 326	71.79 391	93.05 385	86.54 417

miper_lstm_enhance		89.90 261	89.80 257	90.19 298	91.37 377	77.50 321	83.82 404	95.00 265	84.84 277	93.05 249	94.96 252	76.53 328	95.20 370	89.96 184	98.67 164	97.86 193

pmmvs3		80.83 379	78.96 387	86.45 362	87.23 417	77.48 322	84.87 391	82.31 408	63.83 421	85.03 384	89.50 376	49.66 413	93.10 393	73.12 386	95.10 336	88.78 412

PAPR		87.65 308	86.77 319	90.27 293	92.85 340	77.38 323	88.56 337	96.23 221	76.82 361	84.98 385	89.75 373	86.08 236	97.16 308	72.33 389	93.35 376	96.26 288

Vis-MVSNet (Re-imp)		90.42 239	90.16 248	91.20 265	97.66 120	77.32 324	94.33 137	87.66 368	91.20 140	92.99 251	95.13 245	75.40 332	98.28 209	77.86 349	99.19 93	97.99 175

BH-w/o		87.21 319	87.02 314	87.79 346	94.77 293	77.27 325	87.90 343	93.21 307	81.74 314	89.99 324	88.39 388	83.47 258	96.93 320	71.29 395	92.43 392	89.15 408

GA-MVS		87.70 305	86.82 317	90.31 291	93.27 329	77.22 326	84.72 394	92.79 313	85.11 271	89.82 327	90.07 366	66.80 366	97.76 269	84.56 284	94.27 357	95.96 301

TinyColmap		92.00 207	92.76 182	89.71 308	95.62 265	77.02 327	90.72 272	96.17 226	87.70 217	95.26 166	96.29 188	92.54 118	96.45 337	81.77 311	98.77 150	95.66 317

Patchmtry		90.11 254	89.92 254	90.66 283	90.35 392	77.00 328	92.96 186	92.81 311	90.25 163	94.74 193	96.93 143	67.11 363	97.52 283	85.17 271	98.98 116	97.46 227

DIV-MVS_self_test		90.65 233	90.56 241	90.91 276	91.85 366	76.99 329	86.75 366	95.36 257	85.52 263	94.06 211	94.89 254	77.37 316	97.99 243	90.28 171	98.97 121	97.76 206

cl____		90.65 233	90.56 241	90.91 276	91.85 366	76.98 330	86.75 366	95.36 257	85.53 261	94.06 211	94.89 254	77.36 317	97.98 244	90.27 172	98.98 116	97.76 206

pmmvs5		87.87 302	87.14 310	90.07 299	93.26 330	76.97 331	88.89 327	92.18 326	73.71 380	88.36 354	93.89 295	76.86 325	96.73 328	80.32 325	96.81 290	96.51 272

eth_miper_zixun_eth		90.72 230	90.61 239	91.05 268	92.04 361	76.84 332	86.91 361	96.67 198	85.21 267	94.41 200	93.92 293	79.53 295	98.26 213	89.76 188	97.02 280	98.06 164

c3_l		91.32 223	91.42 217	91.00 272	92.29 351	76.79 333	87.52 352	96.42 213	85.76 254	94.72 195	93.89 295	82.73 269	98.16 222	90.93 152	98.55 175	98.04 167

test_vis1_n_1920		89.45 269	89.85 256	88.28 335	93.59 324	76.71 334	90.67 274	97.78 108	79.67 333	90.30 318	96.11 201	76.62 326	92.17 398	90.31 169	93.57 371	95.96 301

MVSTER		89.32 272	88.75 276	91.03 269	90.10 395	76.62 335	90.85 267	94.67 279	82.27 308	95.24 169	95.79 216	61.09 397	98.49 190	90.49 161	98.26 205	97.97 179

miper_ehance_all_eth		90.48 237	90.42 244	90.69 282	91.62 373	76.57 336	86.83 364	96.18 225	83.38 290	94.06 211	92.66 328	82.20 275	98.04 234	89.79 187	97.02 280	97.45 228

cl22		89.02 278	88.50 279	90.59 285	89.76 397	76.45 337	86.62 371	94.03 289	82.98 300	92.65 263	92.49 329	72.05 345	97.53 282	88.93 210	97.02 280	97.78 204

cascas		87.02 326	86.28 329	89.25 317	91.56 375	76.45 337	84.33 399	96.78 190	71.01 397	86.89 373	85.91 404	81.35 283	96.94 318	83.09 296	95.60 321	94.35 358

ADS-MVSNet2		84.01 350	82.20 363	89.41 312	89.04 406	76.37 339	87.57 347	90.98 343	72.71 388	84.46 388	92.45 330	68.08 359	96.48 335	70.58 401	83.97 418	95.38 326

EU-MVSNet		87.39 315	86.71 320	89.44 311	93.40 326	76.11 340	94.93 117	90.00 350	57.17 426	95.71 141	97.37 101	64.77 380	97.68 276	92.67 107	94.37 354	94.52 354

MIMVSNet		87.13 323	86.54 324	88.89 322	96.05 234	76.11 340	94.39 135	88.51 357	81.37 317	88.27 356	96.75 156	72.38 343	95.52 359	65.71 412	95.47 325	95.03 337

IterMVS		90.18 250	90.16 248	90.21 296	93.15 331	75.98 342	87.56 349	92.97 309	86.43 239	94.09 208	96.40 177	78.32 306	97.43 290	87.87 233	94.69 348	97.23 244
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MVS_Test		92.57 192	93.29 169	90.40 290	93.53 325	75.85 343	92.52 204	96.96 175	88.73 191	92.35 278	96.70 161	90.77 160	98.37 205	92.53 111	95.49 324	96.99 255

IB-MVS	77.21 19	83.11 358	81.05 370	89.29 315	91.15 379	75.85 343	85.66 385	86.00 381	79.70 332	82.02 411	86.61 399	48.26 414	98.39 198	77.84 350	92.22 393	93.63 375
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		93.08 172	93.76 154	91.03 269	98.60 38	75.83 345	91.51 250	95.62 241	91.84 114	95.74 138	97.10 131	89.31 187	98.32 207	85.07 278	99.06 104	98.93 71

miper_enhance_ethall		88.42 294	87.87 297	90.07 299	88.67 410	75.52 346	85.10 389	95.59 246	75.68 364	92.49 268	89.45 377	78.96 298	97.88 252	87.86 234	97.02 280	96.81 263

Anonymous20240521		92.86 182	93.57 163	90.74 281	96.57 184	75.50 347	94.15 144	95.60 242	89.38 177	95.90 129	97.90 65	80.39 291	97.96 245	92.60 110	99.68 17	98.75 95

thisisatest0515		84.72 344	82.99 356	89.90 304	92.96 337	75.33 348	84.36 398	83.42 403	77.37 354	88.27 356	86.65 398	53.94 409	98.72 157	82.56 302	97.40 268	95.67 316

MVStest1		84.79 343	84.06 346	86.98 353	77.73 434	74.76 349	91.08 264	85.63 386	77.70 351	96.86 79	97.97 55	41.05 433	88.24 418	92.22 117	96.28 305	97.94 182

PS-MVSNAJ		88.86 285	88.99 271	88.48 332	94.88 286	74.71 350	86.69 368	95.60 242	80.88 322	87.83 362	87.37 396	90.77 160	98.82 136	82.52 303	94.37 354	91.93 397

WTY-MVS		86.93 327	86.50 327	88.24 336	94.96 284	74.64 351	87.19 356	92.07 331	78.29 348	88.32 355	91.59 349	78.06 308	94.27 383	74.88 373	93.15 381	95.80 309

xiu_mvs_v2_base		89.00 281	89.19 265	88.46 333	94.86 288	74.63 352	86.97 359	95.60 242	80.88 322	87.83 362	88.62 385	91.04 155	98.81 141	82.51 304	94.38 353	91.93 397

1314		86.46 331	86.33 328	86.87 357	91.65 372	74.54 353	91.94 234	94.10 288	74.28 376	84.78 387	87.33 397	83.03 264	95.00 372	78.72 345	91.16 401	91.06 404

CHOSEN 280x420		80.04 386	77.97 393	86.23 368	90.13 394	74.53 354	72.87 423	89.59 352	66.38 415	76.29 424	85.32 409	56.96 404	95.36 365	69.49 404	94.72 347	88.79 411

USDC		89.02 278	89.08 267	88.84 323	95.07 283	74.50 355	88.97 325	96.39 214	73.21 383	93.27 239	96.28 190	82.16 276	96.39 339	77.55 353	98.80 146	95.62 320

MVE	59.87 23	73.86 395	72.65 398	77.47 407	87.00 420	74.35 356	61.37 427	60.93 433	67.27 412	69.69 428	86.49 401	81.24 287	72.33 430	56.45 425	83.45 420	85.74 418
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EPNet_dtu		85.63 335	84.37 341	89.40 313	86.30 421	74.33 357	91.64 248	88.26 359	84.84 277	72.96 427	89.85 367	71.27 349	97.69 275	76.60 361	97.62 257	96.18 292
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline1		87.62 309	87.31 304	88.54 329	94.71 298	74.27 358	93.10 182	88.20 361	86.20 244	92.18 284	93.04 316	73.21 339	95.52 359	79.32 341	85.82 416	95.83 308

ttmdpeth		86.91 328	86.57 322	87.91 343	89.68 399	74.24 359	91.49 251	87.09 372	79.84 328	89.46 334	97.86 66	65.42 375	91.04 403	81.57 315	96.74 295	98.44 135

Patchmatch-test		86.10 333	86.01 330	86.38 365	90.63 386	74.22 360	89.57 309	86.69 375	85.73 255	89.81 328	92.83 321	65.24 378	91.04 403	77.82 352	95.78 317	93.88 369

dcpmvs_2		93.96 147	95.01 106	90.82 279	97.60 122	74.04 361	93.68 163	98.85 10	89.80 170	97.82 32	97.01 139	91.14 154	99.21 84	90.56 159	98.59 172	99.19 38

MDA-MVSNet_test_wron		88.16 299	88.23 290	87.93 341	92.22 353	73.71 362	80.71 416	88.84 354	82.52 305	94.88 188	95.14 244	82.70 270	93.61 389	83.28 294	93.80 368	96.46 278

YYNet1		88.17 298	88.24 289	87.93 341	92.21 354	73.62 363	80.75 415	88.77 355	82.51 306	94.99 183	95.11 246	82.70 270	93.70 388	83.33 293	93.83 367	96.48 276

test0.0.03 1		82.48 364	81.47 368	85.48 374	89.70 398	73.57 364	84.73 392	81.64 410	83.07 298	88.13 358	86.61 399	62.86 391	89.10 417	66.24 411	90.29 405	93.77 371

thres600view7		87.66 307	87.10 313	89.36 314	96.05 234	73.17 365	92.72 194	85.31 392	91.89 109	93.29 237	90.97 357	63.42 388	98.39 198	73.23 384	96.99 285	96.51 272

ANet_high		94.83 106	96.28 41	90.47 287	96.65 176	73.16 366	94.33 137	98.74 14	96.39 28	98.09 29	98.93 10	93.37 92	98.70 164	90.38 165	99.68 17	99.53 17

thres100view900		87.35 316	86.89 316	88.72 325	96.14 227	73.09 367	93.00 185	85.31 392	92.13 102	93.26 240	90.96 358	63.42 388	98.28 209	71.27 396	96.54 299	94.79 347

RRT-MVS		92.28 200	93.01 175	90.07 299	94.06 314	73.01 368	95.36 95	97.88 95	92.24 98	95.16 173	97.52 90	78.51 305	99.29 74	90.55 160	95.83 316	97.92 185

tfpn200view9		87.05 325	86.52 325	88.67 326	95.77 254	72.94 369	91.89 237	86.00 381	90.84 146	92.61 264	89.80 369	63.93 384	98.28 209	71.27 396	96.54 299	94.79 347

thres400		87.20 320	86.52 325	89.24 318	95.77 254	72.94 369	91.89 237	86.00 381	90.84 146	92.61 264	89.80 369	63.93 384	98.28 209	71.27 396	96.54 299	96.51 272

baseline2		83.38 357	81.54 367	88.90 321	91.38 376	72.84 371	88.78 331	81.22 413	78.97 343	79.82 419	87.56 393	61.73 395	97.80 262	74.30 378	90.05 406	96.05 298

ECVR-MVS		90.12 253	90.16 248	90.00 303	97.81 105	72.68 372	95.76 79	78.54 423	89.04 184	95.36 159	98.10 44	70.51 352	98.64 174	87.10 245	99.18 95	98.67 108

thres200		85.85 334	85.18 335	87.88 344	94.44 304	72.52 373	89.08 324	86.21 378	88.57 197	91.44 296	88.40 387	64.22 382	98.00 241	68.35 405	95.88 315	93.12 382

MG-MVS		89.54 267	89.80 257	88.76 324	94.88 286	72.47 374	89.60 308	92.44 322	85.82 252	89.48 333	95.98 207	82.85 267	97.74 272	81.87 310	95.27 332	96.08 296

PAPM		81.91 371	80.11 382	87.31 350	93.87 319	72.32 375	84.02 401	93.22 305	69.47 407	76.13 425	89.84 368	72.15 344	97.23 301	53.27 426	89.02 409	92.37 394

SCA		87.43 314	87.21 308	88.10 339	92.01 362	71.98 376	89.43 314	88.11 363	82.26 309	88.71 348	92.83 321	78.65 301	97.59 280	79.61 338	93.30 377	94.75 349

testgi		90.38 243	91.34 220	87.50 348	97.49 129	71.54 377	89.43 314	95.16 261	88.38 201	94.54 198	94.68 266	92.88 111	93.09 394	71.60 394	97.85 245	97.88 190

test1111		90.39 242	90.61 239	89.74 307	98.04 89	71.50 378	95.59 85	79.72 420	89.41 176	95.94 126	98.14 42	70.79 350	98.81 141	88.52 220	99.32 70	98.90 77

gg-mvs-nofinetune		82.10 369	81.02 371	85.34 375	87.46 416	71.04 379	94.74 121	67.56 430	96.44 26	79.43 420	98.99 8	45.24 422	96.15 345	67.18 409	92.17 394	88.85 410

GG-mvs-BLEND				83.24 393	85.06 427	71.03 380	94.99 116	65.55 432		74.09 426	75.51 426	44.57 424	94.46 379	59.57 422	87.54 413	84.24 419

ppachtmachnet_test		88.61 291	88.64 277	88.50 331	91.76 368	70.99 381	84.59 396	92.98 308	79.30 341	92.38 275	93.53 306	79.57 294	97.45 288	86.50 258	97.17 275	97.07 249

our_test_3		87.55 311	87.59 301	87.44 349	91.76 368	70.48 382	83.83 403	90.55 348	79.79 330	92.06 288	92.17 338	78.63 303	95.63 357	84.77 281	94.73 346	96.22 290

CVMVSNet		85.16 339	84.72 337	86.48 361	92.12 358	70.19 383	92.32 217	88.17 362	56.15 427	90.64 311	95.85 211	67.97 361	96.69 329	88.78 215	90.52 404	92.56 392

new_pmnet		81.22 374	81.01 372	81.86 398	90.92 383	70.15 384	84.03 400	80.25 419	70.83 398	85.97 377	89.78 372	67.93 362	84.65 425	67.44 408	91.90 397	90.78 405

KD-MVS_2432*1600		82.17 367	80.75 374	86.42 363	82.04 431	70.09 385	81.75 412	90.80 345	82.56 303	90.37 316	89.30 378	42.90 429	96.11 347	74.47 375	92.55 390	93.06 383

miper_refine_blended		82.17 367	80.75 374	86.42 363	82.04 431	70.09 385	81.75 412	90.80 345	82.56 303	90.37 316	89.30 378	42.90 429	96.11 347	74.47 375	92.55 390	93.06 383

MonoMVSNet		88.46 293	89.28 264	85.98 369	90.52 388	70.07 387	95.31 101	94.81 273	88.38 201	93.47 229	96.13 200	73.21 339	95.07 371	82.61 301	89.12 408	92.81 389

DSMNet-mixed		82.21 366	81.56 365	84.16 387	89.57 402	70.00 388	90.65 275	77.66 425	54.99 428	83.30 401	97.57 84	77.89 310	90.50 407	66.86 410	95.54 323	91.97 396

PatchmatchNet		85.22 338	84.64 338	86.98 353	89.51 403	69.83 389	90.52 278	87.34 371	78.87 345	87.22 371	92.74 325	66.91 365	96.53 332	81.77 311	86.88 414	94.58 353
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EMVS		80.35 383	80.28 381	80.54 402	84.73 428	69.07 390	72.54 424	80.73 416	87.80 213	81.66 413	81.73 420	62.89 390	89.84 410	75.79 369	94.65 349	82.71 422

E-PMN		80.72 380	80.86 373	80.29 403	85.11 426	68.77 391	72.96 422	81.97 409	87.76 215	83.25 402	83.01 419	62.22 394	89.17 416	77.15 358	94.31 356	82.93 421

testing222		80.54 382	78.53 390	86.58 360	92.54 347	68.60 392	86.24 377	82.72 407	83.78 289	82.68 406	84.24 414	39.25 434	95.94 353	60.25 420	95.09 337	95.20 328

reproduce_monomvs		87.13 323	86.90 315	87.84 345	90.92 383	68.15 393	91.19 259	93.75 295	85.84 251	94.21 206	95.83 214	42.99 428	97.10 310	89.46 194	97.88 243	98.26 150

mvs_anonymous		90.37 244	91.30 221	87.58 347	92.17 357	68.00 394	89.84 302	94.73 276	83.82 288	93.22 244	97.40 99	87.54 210	97.40 293	87.94 232	95.05 338	97.34 238

testing91		83.56 356	82.45 360	86.91 356	92.92 338	67.29 395	86.33 376	88.07 364	86.22 243	84.26 391	85.76 405	48.15 416	97.17 306	76.27 365	94.08 365	96.27 287

testing11		81.98 370	80.52 377	86.38 365	92.69 342	67.13 396	85.79 383	84.80 397	82.16 310	81.19 416	85.41 408	45.24 422	96.88 323	74.14 379	93.24 378	95.14 332

CostFormer		83.09 359	82.21 362	85.73 370	89.27 405	67.01 397	90.35 285	86.47 377	70.42 402	83.52 399	93.23 313	61.18 396	96.85 324	77.21 357	88.26 412	93.34 381

PatchT		87.51 312	88.17 293	85.55 373	90.64 385	66.91 398	92.02 229	86.09 380	92.20 99	89.05 340	97.16 124	64.15 383	96.37 341	89.21 205	92.98 386	93.37 380

test-LLR		83.58 355	83.17 354	84.79 381	89.68 399	66.86 399	83.08 406	84.52 398	83.07 298	82.85 403	84.78 412	62.86 391	93.49 390	82.85 297	94.86 342	94.03 364

test-mter		81.21 375	80.01 383	84.79 381	89.68 399	66.86 399	83.08 406	84.52 398	73.85 379	82.85 403	84.78 412	43.66 427	93.49 390	82.85 297	94.86 342	94.03 364

testing99		82.94 361	81.72 364	86.59 359	92.55 345	66.53 401	86.08 380	85.70 384	85.47 264	83.95 394	85.70 406	45.87 420	97.07 313	76.58 362	93.56 372	96.17 294

test2506		85.42 337	84.57 340	87.96 340	97.81 105	66.53 401	96.14 61	56.35 434	89.04 184	93.55 227	98.10 44	42.88 431	98.68 168	88.09 227	99.18 95	98.67 108

PVSNet_0	70.34 21	74.58 394	72.96 397	79.47 404	90.63 386	66.24 403	73.26 421	83.40 404	63.67 422	78.02 421	78.35 425	72.53 341	89.59 412	56.68 423	60.05 429	82.57 423

ETVMVS		79.85 387	77.94 394	85.59 371	92.97 336	66.20 404	86.13 379	80.99 415	81.41 316	83.52 399	83.89 415	41.81 432	94.98 375	56.47 424	94.25 358	95.61 321

WB-MVSnew		84.20 349	83.89 349	85.16 378	91.62 373	66.15 405	88.44 340	81.00 414	76.23 363	87.98 360	87.77 392	84.98 249	93.35 392	62.85 419	94.10 364	95.98 300

testing3		83.66 354	82.52 359	87.08 351	95.84 248	65.84 406	89.80 304	77.17 427	88.17 206	90.84 306	88.63 384	30.95 436	98.11 227	84.05 289	97.19 274	97.28 242

ADS-MVSNet		82.25 365	81.55 366	84.34 385	89.04 406	65.30 407	87.57 347	85.13 396	72.71 388	84.46 388	92.45 330	68.08 359	92.33 397	70.58 401	83.97 418	95.38 326

tpmvs		84.22 348	83.97 347	84.94 379	87.09 418	65.18 408	91.21 258	88.35 358	82.87 301	85.21 380	90.96 358	65.24 378	96.75 327	79.60 340	85.25 417	92.90 388

tpm2		81.46 372	80.35 380	84.80 380	89.90 396	65.14 409	90.44 280	85.36 391	65.82 418	82.05 410	92.44 332	57.94 402	96.69 329	70.71 400	88.49 411	92.56 392

EPMVS		81.17 376	80.37 379	83.58 391	85.58 424	65.08 410	90.31 287	71.34 429	77.31 356	85.80 378	91.30 351	59.38 400	92.70 396	79.99 331	82.34 423	92.96 387

tpm cat1		80.61 381	79.46 384	84.07 388	88.78 408	65.06 411	89.26 320	88.23 360	62.27 423	81.90 412	89.66 375	62.70 393	95.29 368	71.72 392	80.60 425	91.86 399

DeepMVS_CX				53.83 412	70.38 435	64.56 412		48.52 436	33.01 430	65.50 430	74.21 427	56.19 406	46.64 433	38.45 431	70.07 427	50.30 428

PVSNet	76.22 20	82.89 362	82.37 361	84.48 383	93.96 316	64.38 413	78.60 418	88.61 356	71.50 393	84.43 390	86.36 402	74.27 335	94.60 377	69.87 403	93.69 370	94.46 355

TESTMET0.1,1		79.09 390	78.04 392	82.25 397	87.52 415	64.03 414	83.08 406	80.62 417	70.28 403	80.16 418	83.22 418	44.13 425	90.56 406	79.95 332	93.36 375	92.15 395

SSC-MVS3.2		89.88 262	91.06 227	86.31 367	95.90 245	63.76 415	82.68 409	92.43 323	91.42 134	92.37 277	94.58 271	86.34 232	96.60 331	84.35 287	99.50 40	98.57 123

tpm		84.38 347	84.08 345	85.30 376	90.47 390	63.43 416	89.34 317	85.63 386	77.24 357	87.62 366	95.03 250	61.00 398	97.30 297	79.26 342	91.09 402	95.16 330

Syy-MVS		84.81 342	84.93 336	84.42 384	91.71 370	63.36 417	85.89 381	81.49 411	81.03 319	85.13 382	81.64 421	77.44 313	95.00 372	85.94 265	94.12 362	94.91 343

UBG		80.28 385	78.94 388	84.31 386	92.86 339	61.77 418	83.87 402	83.31 405	77.33 355	82.78 405	83.72 416	47.60 418	96.06 349	65.47 413	93.48 374	95.11 335

WBMVS		84.00 351	83.48 351	85.56 372	92.71 341	61.52 419	83.82 404	89.38 353	79.56 335	90.74 308	93.20 314	48.21 415	97.28 298	75.63 370	98.10 223	97.88 190

MDTV_nov1_ep13			83.88 350		89.42 404	61.52 419	88.74 333	87.41 369	73.99 378	84.96 386	94.01 290	65.25 377	95.53 358	78.02 348	93.16 380

WAC-MVS						61.25 421								74.55 374

myMVS_eth3d		79.62 388	78.26 391	83.72 390	91.71 370	61.25 421	85.89 381	81.49 411	81.03 319	85.13 382	81.64 421	32.12 435	95.00 372	71.17 399	94.12 362	94.91 343

UWE-MVS		80.29 384	79.10 385	83.87 389	91.97 364	59.56 423	86.50 375	77.43 426	75.40 368	87.79 364	88.10 390	44.08 426	96.90 322	64.23 414	96.36 303	95.14 332

gm-plane-assit					87.08 419	59.33 424			71.22 394		83.58 417		97.20 303	73.95 380

tpmrst		82.85 363	82.93 357	82.64 395	87.65 413	58.99 425	90.14 292	87.90 366	75.54 366	83.93 395	91.63 348	66.79 368	95.36 365	81.21 320	81.54 424	93.57 379

myMVS_eth3d28		80.97 377	80.42 378	82.62 396	93.35 327	58.25 426	84.70 395	85.62 388	86.31 240	84.04 393	85.20 410	46.00 419	94.07 386	62.93 418	95.65 320	95.53 323

dp		79.28 389	78.62 389	81.24 401	85.97 423	56.45 427	86.91 361	85.26 394	72.97 386	81.45 415	89.17 382	56.01 407	95.45 363	73.19 385	76.68 426	91.82 400

new-patchmatchnet		88.97 282	90.79 235	83.50 392	94.28 308	55.83 428	85.34 388	93.56 299	86.18 245	95.47 151	95.73 222	83.10 262	96.51 334	85.40 270	98.06 226	98.16 158

UWE-MVS-28		74.73 393	73.18 396	79.35 405	85.42 425	55.55 429	87.63 345	65.92 431	74.39 375	77.33 423	88.19 389	47.63 417	89.48 414	39.01 430	93.14 382	93.03 386

dmvs_testset		78.23 392	78.99 386	75.94 408	91.99 363	55.34 430	88.86 328	78.70 422	82.69 302	81.64 414	79.46 423	75.93 329	85.74 423	48.78 428	82.85 422	86.76 416

testing3-2		83.95 352	84.22 344	83.13 394	96.28 213	54.34 431	88.51 338	83.01 406	92.19 100	89.09 339	90.98 356	45.51 421	97.44 289	74.38 377	98.01 232	97.60 218

SSC-MVS		90.16 251	92.96 176	81.78 399	97.88 100	48.48 432	90.75 270	87.69 367	96.02 37	96.70 88	97.63 81	85.60 243	97.80 262	85.73 267	98.60 171	99.06 53

WB-MVS		89.44 270	92.15 199	81.32 400	97.73 112	48.22 433	89.73 305	87.98 365	95.24 42	96.05 122	96.99 140	85.18 246	96.95 317	82.45 305	97.97 237	98.78 91

MVS-HIRNet		78.83 391	80.60 376	73.51 410	93.07 332	47.37 434	87.10 358	78.00 424	68.94 408	77.53 422	97.26 114	71.45 348	94.62 376	63.28 417	88.74 410	78.55 425

PMMVS2		81.31 373	83.44 352	74.92 409	90.52 388	46.49 435	69.19 425	85.23 395	84.30 284	87.95 361	94.71 264	76.95 322	84.36 426	64.07 415	98.09 224	93.89 368

MDTV_nov1_ep13_2view						42.48 436	88.45 339		67.22 413	83.56 398		66.80 366		72.86 387		94.06 363

dongtai		53.72 396	53.79 399	53.51 413	79.69 433	36.70 437	77.18 419	32.53 439	71.69 391	68.63 429	60.79 428	26.65 437	73.11 429	30.67 432	36.29 431	50.73 427

kuosan		43.63 398	44.25 402	41.78 414	66.04 436	34.37 438	75.56 420	32.62 438	53.25 429	50.46 432	51.18 429	25.28 438	49.13 432	13.44 433	30.41 432	41.84 429

tmp_tt		37.97 399	44.33 401	18.88 415	11.80 438	21.54 439	63.51 426	45.66 437	4.23 432	51.34 431	50.48 430	59.08 401	22.11 434	44.50 429	68.35 428	13.00 430

test_method		50.44 397	48.94 400	54.93 411	39.68 437	12.38 440	28.59 428	90.09 349	6.82 431	41.10 433	78.41 424	54.41 408	70.69 431	50.12 427	51.26 430	81.72 424

test123		9.49 401	12.01 404	1.91 416	2.87 439	1.30 441	82.38 410	1.34 441	1.36 434	2.84 435	6.56 433	2.45 439	0.97 435	2.73 434	5.56 433	3.47 431

testmvs		9.02 402	11.42 405	1.81 417	2.77 440	1.13 442	79.44 417	1.90 440	1.18 435	2.65 436	6.80 432	1.95 440	0.87 436	2.62 435	3.45 434	3.44 432

mmdepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

monomultidepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

test_blank		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet_test		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

DCPMVS		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

cdsmvs_eth3d_5k		23.35 400	31.13 403	0.00 418	0.00 441	0.00 443	0.00 429	95.58 248	0.00 436	0.00 437	91.15 353	93.43 90	0.00 437	0.00 436	0.00 435	0.00 433

pcd_1.5k_mvsjas		7.56 403	10.09 406	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	90.77 160	0.00 437	0.00 436	0.00 435	0.00 433

sosnet-low-res		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uncertanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

Regformer		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

ab-mvs-re		7.56 403	10.08 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	90.69 363	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

PC_three_1452									75.31 370	95.87 131	95.75 221	92.93 108	96.34 344	87.18 244	98.68 162	98.04 167

eth-test2					0.00 441

eth-test					0.00 441

test_241102_TWO								98.10 65	91.95 105	97.54 43	97.25 115	95.37 32	99.35 62	93.29 86	99.25 84	98.49 131

9.14			94.81 111		97.49 129		94.11 147	98.37 28	87.56 221	95.38 156	96.03 205	94.66 64	99.08 100	90.70 156	98.97 121

test_0728_THIRD									93.26 78	97.40 54	97.35 107	94.69 63	99.34 65	93.88 59	99.42 51	98.89 78

GSMVS																94.75 349

sam_mvs1												66.64 369				94.75 349

sam_mvs												66.41 370

MTGPA								97.62 117

test_post1							90.21 289				5.85 435	65.36 376	96.00 351	79.61 338

test_post											6.07 434	65.74 374	95.84 355

patchmatchnet-post											91.71 346	66.22 372	97.59 280

MTMP							94.82 119	54.62 435

test9_res														88.16 225	98.40 188	97.83 197

agg_prior2														87.06 247	98.36 198	97.98 176

test_prior2							90.21 289		89.33 179	90.77 307	94.81 258	90.41 170		88.21 221	98.55 175

旧先验2							90.00 297		68.65 409	92.71 262			96.52 333	85.15 273

新几何2							90.02 296

无先验							89.94 298	95.75 238	70.81 399				98.59 180	81.17 321		94.81 345

原ACMM2							89.34 317

testdata2													98.03 235	80.24 328

segment_acmp												92.14 126

testdata1							88.96 326		88.44 200

plane_prior5								97.81 103					98.95 120	89.26 202	98.51 181	98.60 120

plane_prior4											95.59 226

plane_prior2							94.56 130		91.74 122

plane_prior1					97.38 134

n2								0.00 442

nn								0.00 442

door-mid								92.13 330

test11								96.65 199

door								91.26 340

HQP-NCC					96.36 202		91.37 253		87.16 227	88.81 343

ACMP_Plane					96.36 202		91.37 253		87.16 227	88.81 343

BP-MVS														86.55 256

HQP4-MVS										88.81 343			98.61 176			98.15 159

HQP3-MVS								97.31 148							97.73 249

HQP2-MVS												84.76 250

ACMMP++_ref															98.82 142

ACMMP++															99.25 84

Test By Simon												90.61 166

High-resolution multi-view benchmark