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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

MCST-MVS		85.13 22	86.62 24	83.39 17	90.55 14	89.82 17	89.29 21	73.89 22	84.38 30	76.03 30	79.01 32	85.90 21	78.47 12	87.81 17	86.11 33	92.11 1	93.29 22

CSCG		85.28 21	87.68 19	82.49 24	89.95 24	91.99 5	88.82 24	71.20 37	86.41 21	79.63 16	79.26 30	88.36 10	73.94 41	86.64 31	86.67 26	91.40 2	94.41 8

SF-MVS		87.47 8	89.70 8	84.86 8	91.26 6	91.10 8	90.90 6	75.65 8	89.21 9	81.25 7	91.12 8	88.93 7	78.82 10	87.42 20	86.23 30	91.28 3	93.90 13

SteuartSystems-ACMMP		85.99 16	88.31 16	83.27 20	90.73 10	89.84 15	90.27 14	74.31 15	84.56 29	75.88 31	87.32 14	85.04 24	77.31 23	89.01 7	88.46 3	91.14 4	93.96 12
Skip Steuart: Steuart Systems R&D Blog.
APDe-MVS		88.00 6	90.50 6	85.08 5	90.95 7	91.58 7	92.03 1	75.53 12	91.15 5	80.10 14	92.27 5	88.34 11	80.80 5	88.00 15	86.99 19	91.09 5	95.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DeepC-MVS	78.47 2	84.81 25	86.03 29	83.37 18	89.29 32	90.38 12	88.61 26	76.50 1	86.25 22	77.22 24	75.12 41	80.28 45	77.59 21	88.39 10	88.17 6	91.02 6	93.66 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DVP-MVS++		89.14 1	91.86 1	85.97 1	92.55 2	92.38 1	91.69 4	76.31 3	93.31 1	83.11 3	92.44 4	91.18 1	81.17 2	89.55 2	87.93 8	91.01 7	96.21 1

SED-MVS		88.85 2	91.59 3	85.67 2	90.54 15	92.29 3	91.71 3	76.40 2	92.41 3	83.24 2	92.50 3	90.64 4	81.10 3	89.53 3	88.02 7	91.00 8	95.73 3

DPE-MVS		88.63 4	91.29 4	85.53 3	90.87 8	92.20 4	91.98 2	76.00 6	90.55 8	82.09 6	93.85 1	90.75 2	81.25 1	88.62 8	87.59 15	90.96 9	95.48 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MVS_0304		84.63 27	87.25 22	81.59 29	88.58 37	90.50 10	87.82 34	69.16 52	83.82 33	78.46 20	82.32 25	84.97 26	74.56 37	88.16 12	87.72 12	90.94 10	93.24 23

SMA-MVS		87.56 7	90.17 7	84.52 9	91.71 3	90.57 9	90.77 8	75.19 13	90.67 7	80.50 13	86.59 17	88.86 8	78.09 15	89.92 1	89.41 1	90.84 11	95.19 5
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
DVP-MVS		88.67 3	91.62 2	85.22 4	90.47 16	92.36 2	90.69 9	76.15 4	93.08 2	82.75 4	92.19 6	90.71 3	80.45 6	89.27 6	87.91 9	90.82 12	95.84 2
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
HFP-MVS		86.15 15	87.95 18	84.06 13	90.80 9	89.20 24	89.62 19	74.26 16	87.52 14	80.63 11	86.82 16	84.19 29	78.22 14	87.58 18	87.19 17	90.81 13	93.13 25

ACMMPR		85.52 17	87.53 20	83.17 21	90.13 19	89.27 21	89.30 20	73.97 20	86.89 19	77.14 25	86.09 18	83.18 32	77.74 19	87.42 20	87.20 16	90.77 14	92.63 26

ACMMP		83.42 31	85.27 32	81.26 31	88.47 38	88.49 33	88.31 31	72.09 32	83.42 35	72.77 41	82.65 24	78.22 50	75.18 34	86.24 38	85.76 35	90.74 15	92.13 31
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
PGM-MVS		84.42 28	86.29 28	82.23 25	90.04 22	88.82 26	89.23 22	71.74 35	82.82 39	74.61 34	84.41 23	82.09 35	77.03 27	87.13 25	86.73 25	90.73 16	92.06 32

DeepC-MVS_fast	78.24 3	84.27 29	85.50 31	82.85 22	90.46 17	89.24 22	87.83 33	74.24 17	84.88 25	76.23 29	75.26 40	81.05 43	77.62 20	88.02 14	87.62 14	90.69 17	92.41 28
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SD-MVS		86.96 10	89.45 9	84.05 14	90.13 19	89.23 23	89.77 18	74.59 14	89.17 10	80.70 10	89.93 11	89.67 5	78.47 12	87.57 19	86.79 23	90.67 18	93.76 16
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
EC-MVSNet		79.44 48	81.35 47	77.22 52	82.95 63	84.67 63	81.31 62	63.65 92	72.47 69	68.75 57	73.15 47	78.33 49	75.99 32	86.06 40	83.96 49	90.67 18	90.79 41

TSAR-MVS + MP.		86.88 11	89.23 10	84.14 12	89.78 26	88.67 30	90.59 10	73.46 26	88.99 11	80.52 12	91.26 7	88.65 9	79.91 8	86.96 29	86.22 31	90.59 20	93.83 14
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
APD-MVS		86.84 12	88.91 14	84.41 10	90.66 11	90.10 13	90.78 7	75.64 9	87.38 16	78.72 18	90.68 10	86.82 17	80.15 7	87.13 25	86.45 29	90.51 21	93.83 14
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVS		84.74 26	86.43 27	82.77 23	89.48 30	88.13 39	88.64 25	73.93 21	84.92 24	76.77 27	81.94 27	83.50 31	77.29 25	86.92 30	86.49 28	90.49 22	93.14 24

XVS					86.63 46	88.68 27	85.00 47			71.81 46		81.92 37				90.47 23

X-MVStestdata					86.63 46	88.68 27	85.00 47			71.81 46		81.92 37				90.47 23

X-MVS		83.23 33	85.20 33	80.92 34	89.71 27	88.68 27	88.21 32	73.60 23	82.57 40	71.81 46	77.07 33	81.92 37	71.72 58	86.98 28	86.86 21	90.47 23	92.36 29

NCCC		85.34 19	86.59 25	83.88 15	91.48 4	88.88 25	89.79 17	75.54 11	86.67 20	77.94 23	76.55 35	84.99 25	78.07 16	88.04 13	87.68 13	90.46 26	93.31 21

CNVR-MVS		86.36 14	88.19 17	84.23 11	91.33 5	89.84 15	90.34 11	75.56 10	87.36 17	78.97 17	81.19 29	86.76 18	78.74 11	89.30 5	88.58 2	90.45 27	94.33 10

MP-MVS		85.50 18	87.40 21	83.28 19	90.65 12	89.51 20	89.16 23	74.11 18	83.70 34	78.06 22	85.54 20	84.89 28	77.31 23	87.40 22	87.14 18	90.41 28	93.65 19
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
3Dnovator+	75.73 4	82.40 35	82.76 39	81.97 28	88.02 39	89.67 18	86.60 38	71.48 36	81.28 44	78.18 21	64.78 92	77.96 52	77.13 26	87.32 23	86.83 22	90.41 28	91.48 36

ACMMP_NAP		86.52 13	89.01 11	83.62 16	90.28 18	90.09 14	90.32 13	74.05 19	88.32 13	79.74 15	87.04 15	85.59 23	76.97 28	89.35 4	88.44 4	90.35 30	94.27 11

CS-MVS		79.22 51	81.11 50	77.01 54	81.36 77	84.03 67	80.35 69	63.25 96	73.43 66	70.37 53	74.10 46	76.03 59	76.40 30	86.32 37	83.95 50	90.34 31	89.93 49

CDPH-MVS		82.64 34	85.03 34	79.86 39	89.41 31	88.31 36	88.32 30	71.84 34	80.11 46	67.47 65	82.09 26	81.44 41	71.85 56	85.89 41	86.15 32	90.24 32	91.25 38

LGP-MVS_train		79.83 43	81.22 49	78.22 48	86.28 49	85.36 58	86.76 37	69.59 46	77.34 51	65.14 76	75.68 37	70.79 85	71.37 62	84.60 50	84.01 47	90.18 33	90.74 42

HPM-MVS++		87.09 9	88.92 13	84.95 6	92.61 1	87.91 40	90.23 15	76.06 5	88.85 12	81.20 9	87.33 13	87.93 12	79.47 9	88.59 9	88.23 5	90.15 34	93.60 20

3Dnovator	73.76 5	79.75 45	80.52 55	78.84 43	84.94 59	87.35 41	84.43 52	65.54 75	78.29 50	73.97 36	63.00 100	75.62 62	74.07 40	85.00 47	85.34 39	90.11 35	89.04 56

DPM-MVS		83.30 32	84.33 35	82.11 26	89.56 28	88.49 33	90.33 12	73.24 27	83.85 32	76.46 28	72.43 52	82.65 33	73.02 48	86.37 35	86.91 20	90.03 36	89.62 53

ETV-MVS		77.32 64	78.81 63	75.58 62	82.24 71	83.64 75	79.98 71	64.02 88	69.64 78	63.90 83	70.89 60	69.94 91	73.41 44	85.39 45	83.91 51	89.92 37	88.31 61

ACMP	73.23 7	79.79 44	80.53 54	78.94 42	85.61 52	85.68 53	85.61 43	69.59 46	77.33 52	71.00 52	74.45 43	69.16 96	71.88 54	83.15 67	83.37 55	89.92 37	90.57 45
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SPE-MVS-test		78.79 58	80.72 52	76.53 57	81.11 82	83.88 70	79.69 78	63.72 91	73.80 63	69.95 55	75.40 39	76.17 56	74.85 35	84.50 53	82.78 60	89.87 39	88.54 60

train_agg		84.86 24	87.21 23	82.11 26	90.59 13	85.47 55	89.81 16	73.55 25	83.95 31	73.30 39	89.84 12	87.23 15	75.61 33	86.47 33	85.46 38	89.78 40	92.06 32

TSAR-MVS + GP.		83.69 30	86.58 26	80.32 36	85.14 54	86.96 44	84.91 50	70.25 41	84.71 28	73.91 37	85.16 21	85.63 22	77.92 17	85.44 42	85.71 36	89.77 41	92.45 27

ACMM	72.26 8	78.86 57	78.13 66	79.71 40	86.89 45	83.40 77	86.02 40	70.50 39	75.28 56	71.49 50	63.01 99	69.26 95	73.57 43	84.11 56	83.98 48	89.76 42	87.84 65
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TPM-MVS					90.07 21	88.36 35	88.45 29			77.10 26	75.60 38	83.98 30	71.33 63			89.75 43	89.62 53
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
OPM-MVS		79.68 47	79.28 62	80.15 38	87.99 40	86.77 46	88.52 28	72.72 29	64.55 105	67.65 64	67.87 78	74.33 67	74.31 39	86.37 35	85.25 40	89.73 44	89.81 51
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MSP-MVS		88.09 5	90.84 5	84.88 7	90.00 23	91.80 6	91.63 5	75.80 7	91.99 4	81.23 8	92.54 2	89.18 6	80.89 4	87.99 16	87.91 9	89.70 45	94.51 7
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
CANet		81.62 39	83.41 36	79.53 41	87.06 43	88.59 31	85.47 45	67.96 58	76.59 54	74.05 35	74.69 42	81.98 36	72.98 49	86.14 39	85.47 37	89.68 46	90.42 46

MVS_111021_HR		80.13 42	81.46 46	78.58 45	85.77 51	85.17 59	83.45 55	69.28 49	74.08 62	70.31 54	74.31 44	75.26 63	73.13 46	86.46 34	85.15 41	89.53 47	89.81 51

IS_MVSNet		73.33 88	77.34 77	68.65 121	81.29 78	83.47 76	74.45 132	63.58 94	65.75 96	48.49 157	67.11 84	70.61 86	54.63 175	84.51 52	83.58 54	89.48 48	86.34 82

DELS-MVS		79.15 55	81.07 51	76.91 55	83.54 61	87.31 42	84.45 51	64.92 80	69.98 73	69.34 56	71.62 56	76.26 55	69.84 68	86.57 32	85.90 34	89.39 49	89.88 50
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
UniMVSNet_NR-MVSNet		70.59 111	72.19 110	68.72 119	77.72 114	80.72 105	73.81 147	69.65 45	61.99 125	43.23 184	60.54 109	57.50 144	58.57 143	79.56 118	81.07 76	89.34 50	83.97 112

casdiffmvs_mvg		77.79 62	79.55 61	75.73 61	81.56 74	84.70 62	82.12 57	64.26 87	74.27 60	67.93 62	70.83 61	74.66 65	69.19 76	83.33 66	81.94 66	89.29 51	87.14 73
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EIA-MVS		75.64 75	76.60 83	74.53 73	82.43 68	83.84 71	78.32 95	62.28 120	65.96 94	63.28 87	68.95 70	67.54 107	71.61 60	82.55 73	81.63 70	89.24 52	85.72 87

PHI-MVS		82.36 36	85.89 30	78.24 47	86.40 48	89.52 19	85.52 44	69.52 48	82.38 42	65.67 73	81.35 28	82.36 34	73.07 47	87.31 24	86.76 24	89.24 52	91.56 35

sasdasda		79.16 53	82.37 42	75.41 63	82.33 69	86.38 50	80.80 65	63.18 98	82.90 37	67.34 66	72.79 49	76.07 57	69.62 69	83.46 64	84.41 45	89.20 54	90.60 43

canonicalmvs		79.16 53	82.37 42	75.41 63	82.33 69	86.38 50	80.80 65	63.18 98	82.90 37	67.34 66	72.79 49	76.07 57	69.62 69	83.46 64	84.41 45	89.20 54	90.60 43

MSLP-MVS++		82.09 37	82.66 40	81.42 30	87.03 44	87.22 43	85.82 42	70.04 42	80.30 45	78.66 19	68.67 74	81.04 44	77.81 18	85.19 46	84.88 43	89.19 56	91.31 37

HQP-MVS		81.19 40	83.27 37	78.76 44	87.40 42	85.45 56	86.95 36	70.47 40	81.31 43	66.91 70	79.24 31	76.63 54	71.67 59	84.43 54	83.78 52	89.19 56	92.05 34

EPP-MVSNet		74.00 84	77.41 75	70.02 106	80.53 88	83.91 69	74.99 126	62.68 113	65.06 100	49.77 152	68.68 73	72.09 77	63.06 112	82.49 75	80.73 81	89.12 58	88.91 57

NR-MVSNet		68.79 132	70.56 120	66.71 150	77.48 117	79.54 117	73.52 151	69.20 50	61.20 133	39.76 191	58.52 121	50.11 196	51.37 184	80.26 108	80.71 86	88.97 59	83.59 118

PVSNet_Blended_VisFu		76.57 67	77.90 67	75.02 66	80.56 87	86.58 48	79.24 83	66.18 69	64.81 102	68.18 60	65.61 86	71.45 79	67.05 85	84.16 55	81.80 68	88.90 60	90.92 40

TranMVSNet+NR-MVSNet		69.25 127	70.81 119	67.43 134	77.23 119	79.46 119	73.48 152	69.66 44	60.43 138	39.56 192	58.82 120	53.48 172	55.74 168	79.59 116	81.21 74	88.89 61	82.70 122

QAPM		78.47 59	80.22 58	76.43 58	85.03 56	86.75 47	80.62 68	66.00 72	73.77 64	65.35 75	65.54 88	78.02 51	72.69 50	83.71 59	83.36 56	88.87 62	90.41 47

MGCFI-Net		76.55 68	81.71 44	70.52 98	81.71 73	84.62 64	75.02 125	62.17 121	82.91 36	53.58 130	72.78 51	75.87 61	61.75 127	82.96 69	82.61 62	88.86 63	90.26 48

casdiffmvs		76.76 66	78.46 65	74.77 69	80.32 91	83.73 74	80.65 67	63.24 97	73.58 65	66.11 72	69.39 69	74.09 68	69.49 73	82.52 74	79.35 113	88.84 64	86.52 80
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CPTT-MVS		81.77 38	83.10 38	80.21 37	85.93 50	86.45 49	87.72 35	70.98 38	82.54 41	71.53 49	74.23 45	81.49 40	76.31 31	82.85 71	81.87 67	88.79 65	92.26 30

Effi-MVS+		75.28 77	76.20 84	74.20 76	81.15 80	83.24 80	81.11 63	63.13 101	66.37 90	60.27 94	64.30 96	68.88 100	70.93 66	81.56 80	81.69 69	88.61 66	87.35 68

UniMVSNet (Re)		69.53 123	71.90 113	66.76 148	76.42 123	80.93 101	72.59 157	68.03 57	61.75 128	41.68 189	58.34 127	57.23 146	53.27 180	79.53 119	80.62 90	88.57 67	84.90 104

PCF-MVS	73.28 6	79.42 49	80.41 56	78.26 46	84.88 60	88.17 37	86.08 39	69.85 43	75.23 57	68.43 58	68.03 77	78.38 48	71.76 57	81.26 91	80.65 89	88.56 68	91.18 39
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
GeoE		74.23 82	74.84 91	73.52 78	80.42 90	81.46 95	79.77 75	61.06 131	67.23 87	63.67 84	59.56 116	68.74 102	67.90 82	80.25 109	79.37 112	88.31 69	87.26 71

test2506		71.72 100	72.95 104	70.29 101	81.49 75	83.27 78	75.74 114	67.59 62	68.19 82	49.81 151	61.15 104	49.73 198	58.82 141	84.76 48	82.94 57	88.27 70	80.63 143

ECVR-MVS		72.20 96	73.91 96	70.20 103	81.49 75	83.27 78	75.74 114	67.59 62	68.19 82	49.31 155	55.77 138	62.00 125	58.82 141	84.76 48	82.94 57	88.27 70	80.41 147

MAR-MVS		79.21 52	80.32 57	77.92 49	87.46 41	88.15 38	83.95 53	67.48 64	74.28 59	68.25 59	64.70 93	77.04 53	72.17 52	85.42 43	85.00 42	88.22 72	87.62 67
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
Fast-Effi-MVS+		73.11 90	73.66 97	72.48 82	77.72 114	80.88 104	78.55 92	58.83 163	65.19 99	60.36 93	59.98 113	62.42 124	71.22 64	81.66 77	80.61 91	88.20 73	84.88 105

ET-MVSNet_ETH3D		72.46 95	74.19 93	70.44 99	62.50 207	81.17 99	79.90 74	62.46 118	64.52 106	57.52 107	71.49 58	59.15 137	72.08 53	78.61 131	81.11 75	88.16 74	83.29 120

OMC-MVS		80.26 41	82.59 41	77.54 50	83.04 62	85.54 54	83.25 56	65.05 79	87.32 18	72.42 42	72.04 54	78.97 47	73.30 45	83.86 57	81.60 71	88.15 75	88.83 58

AdaColmap		79.74 46	78.62 64	81.05 33	89.23 33	86.06 52	84.95 49	71.96 33	79.39 49	75.51 32	63.16 98	68.84 101	76.51 29	83.55 61	82.85 59	88.13 76	86.46 81

test1111		71.56 102	73.44 99	69.38 114	81.16 79	82.95 83	74.99 126	67.68 60	66.89 88	46.33 171	55.19 144	60.91 128	57.99 149	84.59 51	82.70 61	88.12 77	80.85 140

OpenMVS	70.44 10	76.15 72	76.82 82	75.37 65	85.01 57	84.79 61	78.99 87	62.07 122	71.27 72	67.88 63	57.91 129	72.36 76	70.15 67	82.23 76	81.41 72	88.12 77	87.78 66

FA-MVS(training)		73.66 85	74.95 90	72.15 83	78.63 106	80.46 109	78.92 89	54.79 178	69.71 77	65.37 74	62.04 101	66.89 110	67.10 84	80.72 98	79.87 100	88.10 79	84.97 102

UA-Net		74.47 81	77.80 69	70.59 97	85.33 53	85.40 57	73.54 150	65.98 73	60.65 136	56.00 115	72.11 53	79.15 46	54.63 175	83.13 68	82.25 64	88.04 80	81.92 132

DU-MVS		69.63 122	70.91 118	68.13 125	75.99 125	79.54 117	73.81 147	69.20 50	61.20 133	43.23 184	58.52 121	53.50 170	58.57 143	79.22 123	80.45 92	87.97 81	83.97 112

FC-MVSNet-train		72.60 93	75.07 89	69.71 109	81.10 83	78.79 127	73.74 149	65.23 78	66.10 93	53.34 131	70.36 64	63.40 121	56.92 159	81.44 84	80.96 78	87.93 82	84.46 110

IB-MVS	66.94 12	71.21 107	71.66 115	70.68 93	79.18 101	82.83 87	72.61 156	61.77 126	59.66 141	63.44 86	53.26 161	59.65 135	59.16 140	76.78 153	82.11 65	87.90 83	87.33 69
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
PVSNet_BlendedMVS		76.21 70	77.52 72	74.69 70	79.46 99	83.79 72	77.50 102	64.34 85	69.88 74	71.88 44	68.54 75	70.42 87	67.05 85	83.48 62	79.63 104	87.89 84	86.87 75

PVSNet_Blended		76.21 70	77.52 72	74.69 70	79.46 99	83.79 72	77.50 102	64.34 85	69.88 74	71.88 44	68.54 75	70.42 87	67.05 85	83.48 62	79.63 104	87.89 84	86.87 75

DeepPCF-MVS	79.04 1	85.30 20	88.93 12	81.06 32	88.77 36	90.48 11	85.46 46	73.08 28	90.97 6	73.77 38	84.81 22	85.95 20	77.43 22	88.22 11	87.73 11	87.85 86	94.34 9

thisisatest0530		71.48 104	73.01 103	69.70 110	73.83 153	78.62 129	74.53 131	59.12 157	64.13 108	58.63 100	64.60 94	58.63 139	64.27 105	80.28 107	80.17 98	87.82 87	84.64 108

TAPA-MVS	71.42 9	77.69 63	80.05 59	74.94 67	80.68 86	84.52 65	81.36 61	63.14 100	84.77 26	64.82 78	68.72 72	75.91 60	71.86 55	81.62 78	79.55 108	87.80 88	85.24 97
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
tttt0517		71.41 105	72.95 104	69.60 111	73.70 155	78.70 128	74.42 135	59.12 157	63.89 112	58.35 103	64.56 95	58.39 141	64.27 105	80.29 106	80.17 98	87.74 89	84.69 107

viewmacassd2359aftdt		75.85 73	77.01 80	74.49 74	79.69 97	82.87 86	81.77 58	61.06 131	69.37 79	67.26 68	66.73 85	71.63 78	69.48 74	81.51 82	80.20 95	87.69 90	86.77 78

MVS_Test		75.37 76	77.13 79	73.31 80	79.07 102	81.32 97	79.98 71	60.12 147	69.72 76	64.11 82	70.53 63	73.22 71	68.90 77	80.14 111	79.48 110	87.67 91	85.50 91

DI_MVS_pp		75.13 78	76.12 85	73.96 77	78.18 108	81.55 92	80.97 64	62.54 115	68.59 80	65.13 77	61.43 103	74.81 64	69.32 75	81.01 96	79.59 106	87.64 92	85.89 84

viewmanbaseed2359cas		76.36 69	77.87 68	74.60 72	79.81 95	82.88 85	81.69 60	61.02 133	72.14 71	67.97 61	69.61 67	72.45 75	69.53 71	81.53 81	79.83 101	87.57 93	86.65 79

MVSTER		72.06 97	74.24 92	69.51 112	70.39 183	75.97 158	76.91 109	57.36 172	64.64 104	61.39 91	68.86 71	63.76 119	63.46 109	81.44 84	79.70 103	87.56 94	85.31 96

TSAR-MVS + ACMM		85.10 23	88.81 15	80.77 35	89.55 29	88.53 32	88.59 27	72.55 30	87.39 15	71.90 43	90.95 9	87.55 13	74.57 36	87.08 27	86.54 27	87.47 95	93.67 17

CLD-MVS		79.35 50	81.23 48	77.16 53	85.01 57	86.92 45	85.87 41	60.89 135	80.07 48	75.35 33	72.96 48	73.21 72	68.43 81	85.41 44	84.63 44	87.41 96	85.44 93
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Effi-MVS+-dtu		71.82 99	71.86 114	71.78 87	78.77 103	80.47 108	78.55 92	61.67 129	60.68 135	55.49 116	58.48 123	65.48 114	68.85 78	76.92 150	75.55 162	87.35 97	85.46 92

WR-MVS		63.03 173	67.40 158	57.92 191	75.14 138	77.60 145	60.56 205	66.10 70	54.11 181	23.88 214	53.94 155	53.58 168	34.50 210	73.93 169	77.71 132	87.35 97	80.94 139

v144192		69.34 126	68.68 144	70.12 104	74.06 149	80.54 106	78.08 98	60.54 139	54.99 174	54.13 123	52.92 168	52.80 181	66.73 92	77.13 148	76.72 149	87.15 99	85.63 88

EPNet		79.08 56	80.62 53	77.28 51	88.90 35	83.17 82	83.65 54	72.41 31	74.41 58	67.15 69	76.78 34	74.37 66	64.43 104	83.70 60	83.69 53	87.15 99	88.19 62
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EG-PatchMatch MVS		67.24 153	66.94 161	67.60 132	78.73 104	81.35 96	73.28 154	59.49 153	46.89 206	51.42 143	43.65 200	53.49 171	55.50 171	81.38 86	80.66 88	87.15 99	81.17 138

v1144		69.93 120	69.36 134	70.61 95	74.89 141	80.93 101	79.11 85	60.64 137	55.97 166	55.31 118	53.85 156	54.14 163	66.54 96	78.10 136	77.44 139	87.14 102	85.09 99

anonymousdsp		65.28 163	67.98 151	62.13 172	58.73 216	73.98 172	67.10 179	50.69 199	48.41 202	47.66 165	54.27 150	52.75 182	61.45 131	76.71 154	80.20 95	87.13 103	89.53 55

PLC	68.99 11	75.68 74	75.31 87	76.12 60	82.94 64	81.26 98	79.94 73	66.10 70	77.15 53	66.86 71	59.13 119	68.53 103	73.73 42	80.38 104	79.04 114	87.13 103	81.68 134
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v10		70.22 116	69.76 129	70.74 91	74.79 142	80.30 113	79.22 84	59.81 151	57.71 152	56.58 113	54.22 154	55.31 156	66.95 88	78.28 134	77.47 138	87.12 105	85.07 100

v1192		69.50 124	68.83 140	70.29 101	74.49 145	80.92 103	78.55 92	60.54 139	55.04 172	54.21 121	52.79 170	52.33 183	66.92 89	77.88 139	77.35 142	87.04 106	85.51 90

v1921920		69.03 129	68.32 148	69.86 107	74.03 150	80.37 110	77.55 100	60.25 144	54.62 176	53.59 129	52.36 174	51.50 189	66.75 91	77.17 147	76.69 151	86.96 107	85.56 89

v2v482		70.05 119	69.46 133	70.74 91	74.62 144	80.32 112	79.00 86	60.62 138	57.41 154	56.89 110	55.43 143	55.14 158	66.39 99	77.25 146	77.14 144	86.90 108	83.57 119

Vis-MVSNet		72.77 92	77.20 78	67.59 133	74.19 148	84.01 68	76.61 113	61.69 127	60.62 137	50.61 147	70.25 65	71.31 82	55.57 170	83.85 58	82.28 63	86.90 108	88.08 63
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PEN-MVS		62.96 174	65.77 168	59.70 184	73.98 151	75.45 162	63.39 198	67.61 61	52.49 187	25.49 213	53.39 158	49.12 200	40.85 203	71.94 181	77.26 143	86.86 110	80.72 142

v8		70.23 115	69.86 127	70.67 94	74.69 143	79.82 115	78.79 90	59.18 156	58.80 145	58.20 104	55.00 145	57.33 145	66.31 100	77.51 142	76.71 150	86.82 111	83.88 115

ACMH+	66.54 13	71.36 106	70.09 124	72.85 81	82.59 66	81.13 100	78.56 91	68.04 56	61.55 129	52.52 138	51.50 178	54.14 163	68.56 80	78.85 128	79.50 109	86.82 111	83.94 114

v1240		68.64 134	67.89 154	69.51 112	73.89 152	80.26 114	76.73 111	59.97 150	53.43 184	53.08 133	51.82 177	50.84 192	66.62 93	76.79 152	76.77 148	86.78 113	85.34 95

DCV-MVSNet		73.65 86	75.78 86	71.16 90	80.19 92	79.27 121	77.45 104	61.68 128	66.73 89	58.72 99	65.31 89	69.96 90	62.19 117	81.29 90	80.97 77	86.74 114	86.91 74

GBi-Net		70.78 108	73.37 101	67.76 126	72.95 160	78.00 135	75.15 120	62.72 108	64.13 108	51.44 140	58.37 124	69.02 97	57.59 151	81.33 87	80.72 82	86.70 115	82.02 126

test1		70.78 108	73.37 101	67.76 126	72.95 160	78.00 135	75.15 120	62.72 108	64.13 108	51.44 140	58.37 124	69.02 97	57.59 151	81.33 87	80.72 82	86.70 115	82.02 126

FMVSNet2		70.39 114	72.67 108	67.72 129	72.95 160	78.00 135	75.15 120	62.69 112	63.29 116	51.25 144	55.64 139	68.49 104	57.59 151	80.91 97	80.35 94	86.70 115	82.02 126

v7n		67.05 156	66.94 161	67.17 140	72.35 165	78.97 122	73.26 155	58.88 162	51.16 195	50.90 145	48.21 191	50.11 196	60.96 132	77.70 140	77.38 140	86.68 118	85.05 101

WR-MVS_H		61.83 188	65.87 167	57.12 194	71.72 170	76.87 149	61.45 203	66.19 68	51.97 192	22.92 218	53.13 165	52.30 185	33.80 211	71.03 188	75.00 165	86.65 119	80.78 141

MSDG		71.52 103	69.87 126	73.44 79	82.21 72	79.35 120	79.52 79	64.59 82	66.15 92	61.87 88	53.21 163	56.09 153	65.85 102	78.94 127	78.50 121	86.60 120	76.85 172

FMVSNet3		70.49 112	72.90 106	67.67 131	72.88 163	77.98 138	74.96 129	62.72 108	64.13 108	51.44 140	58.37 124	69.02 97	57.43 154	79.43 121	79.57 107	86.59 121	81.81 133

MVS_111021_LR		78.13 61	79.85 60	76.13 59	81.12 81	81.50 94	80.28 70	65.25 77	76.09 55	71.32 51	76.49 36	72.87 74	72.21 51	82.79 72	81.29 73	86.59 121	87.91 64

DTE-MVSNet		61.85 186	64.96 177	58.22 190	74.32 147	74.39 171	61.01 204	67.85 59	51.76 194	21.91 221	53.28 160	48.17 201	37.74 207	72.22 178	76.44 153	86.52 123	78.49 161

baseline2		69.69 121	70.27 123	69.01 117	75.72 132	77.13 148	73.82 146	58.94 161	61.35 131	57.09 109	61.68 102	57.17 147	61.99 121	78.10 136	76.58 152	86.48 124	79.85 151

thisisatest0515		67.40 151	68.78 141	65.80 154	70.02 185	75.24 165	69.36 169	57.37 171	54.94 175	53.67 128	55.53 142	54.85 159	58.00 148	78.19 135	78.91 117	86.39 125	83.78 116

FMVSNet1		68.84 131	70.47 122	66.94 145	71.35 177	77.68 143	74.71 130	62.35 119	56.93 157	49.94 150	50.01 184	64.59 116	57.07 156	81.33 87	80.72 82	86.25 126	82.00 129

UGNet		72.78 91	77.67 70	67.07 143	71.65 172	83.24 80	75.20 119	63.62 93	64.93 101	56.72 111	71.82 55	73.30 69	49.02 188	81.02 95	80.70 87	86.22 127	88.67 59
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
Anonymous20231211		71.90 98	72.48 109	71.21 89	80.14 93	81.53 93	76.92 107	62.89 104	64.46 107	58.94 96	43.80 199	70.98 84	62.22 116	80.70 99	80.19 97	86.18 128	85.73 86

tfpn200view9		68.11 137	68.72 143	67.40 135	77.83 112	78.93 123	74.28 137	62.81 105	56.64 159	46.82 167	52.65 171	53.47 173	56.59 160	80.41 101	78.43 122	86.11 129	80.52 145

CANet_DTU		73.29 89	76.96 81	69.00 118	77.04 120	82.06 90	79.49 80	56.30 175	67.85 85	53.29 132	71.12 59	70.37 89	61.81 126	81.59 79	80.96 78	86.09 130	84.73 106

CP-MVSNet		62.68 176	65.49 171	59.40 187	71.84 168	75.34 163	62.87 200	67.04 65	52.64 186	27.19 211	53.38 159	48.15 202	41.40 201	71.26 184	75.68 159	86.07 131	82.00 129

ACMH	65.37 14	70.71 110	70.00 125	71.54 88	82.51 67	82.47 89	77.78 99	68.13 55	56.19 164	46.06 174	54.30 148	51.20 190	68.68 79	80.66 100	80.72 82	86.07 131	84.45 111
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres600view7		67.68 145	68.43 147	66.80 147	77.90 109	78.86 125	73.84 145	62.75 106	56.07 165	44.70 182	52.85 169	52.81 180	55.58 169	80.41 101	77.77 131	86.05 133	80.28 148

thres200		67.98 139	68.55 146	67.30 138	77.89 111	78.86 125	74.18 141	62.75 106	56.35 162	46.48 170	52.98 167	53.54 169	56.46 161	80.41 101	77.97 129	86.05 133	79.78 153

CNLPA		77.20 65	77.54 71	76.80 56	82.63 65	84.31 66	79.77 75	64.64 81	85.17 23	73.18 40	56.37 136	69.81 92	74.53 38	81.12 94	78.69 119	86.04 135	87.29 70

TSAR-MVS + COLMAP		78.34 60	81.64 45	74.48 75	80.13 94	85.01 60	81.73 59	65.93 74	84.75 27	61.68 89	85.79 19	66.27 112	71.39 61	82.91 70	80.78 80	86.01 136	85.98 83

LS3D		74.08 83	73.39 100	74.88 68	85.05 55	82.62 88	79.71 77	68.66 53	72.82 67	58.80 98	57.61 130	61.31 127	71.07 65	80.32 105	78.87 118	86.00 137	80.18 149

Anonymous202405211			72.16 112		80.85 85	81.85 91	76.88 110	65.40 76	62.89 120		46.35 195	67.99 106	62.05 119	81.15 93	80.38 93	85.97 138	84.50 109

PS-CasMVS		62.38 182	65.06 174	59.25 188	71.73 169	75.21 167	62.77 201	66.99 66	51.94 193	26.96 212	52.00 176	47.52 205	41.06 202	71.16 187	75.60 160	85.97 138	81.97 131

thres400		67.95 140	68.62 145	67.17 140	77.90 109	78.59 130	74.27 138	62.72 108	56.34 163	45.77 176	53.00 166	53.35 176	56.46 161	80.21 110	78.43 122	85.91 140	80.43 146

thres100view900		67.60 149	68.02 150	67.12 142	77.83 112	77.75 142	73.90 144	62.52 116	56.64 159	46.82 167	52.65 171	53.47 173	55.92 165	78.77 129	77.62 134	85.72 141	79.23 157

Vis-MVSNet (Re-imp)		67.83 143	73.52 98	61.19 176	78.37 107	76.72 152	66.80 182	62.96 102	65.50 98	34.17 203	67.19 83	69.68 93	39.20 206	79.39 122	79.44 111	85.68 142	76.73 173

baseline1		70.10 118	72.17 111	67.69 130	79.74 96	76.80 150	73.91 143	64.38 84	62.74 121	48.30 159	64.94 90	64.08 118	54.17 177	81.46 83	78.92 116	85.66 143	76.22 174

V42		68.76 133	69.63 130	67.74 128	64.93 203	78.01 134	78.30 96	56.48 174	58.65 146	56.30 114	54.26 152	57.03 148	64.85 103	77.47 143	77.01 146	85.60 144	84.96 103

TransMVSNet (Re)		64.74 166	65.66 169	63.66 167	77.40 118	75.33 164	69.86 165	62.67 114	47.63 204	41.21 190	50.01 184	52.33 183	45.31 194	79.57 117	77.69 133	85.49 145	77.07 171

IterMVS-LS		71.69 101	72.82 107	70.37 100	77.54 116	76.34 155	75.13 123	60.46 141	61.53 130	57.57 106	64.89 91	67.33 108	66.04 101	77.09 149	77.37 141	85.48 146	85.18 98
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs_AUTHOR		74.91 79	77.47 74	71.92 85	75.60 135	80.50 107	79.48 81	60.02 149	72.41 70	64.39 80	70.63 62	73.27 70	66.55 94	79.97 112	78.34 124	85.46 147	87.17 72

UniMVSNet_ETH3D		67.18 155	67.03 160	67.36 136	74.44 146	78.12 133	74.07 142	66.38 67	52.22 189	46.87 166	48.64 189	51.84 187	56.96 157	77.29 145	78.53 120	85.42 148	82.59 123

Baseline_NR-MVSNet		67.53 150	68.77 142	66.09 153	75.99 125	74.75 169	72.43 158	68.41 54	61.33 132	38.33 196	51.31 179	54.13 165	56.03 164	79.22 123	78.19 126	85.37 149	82.45 124

Fast-Effi-MVS+-dtu		68.34 135	69.47 132	67.01 144	75.15 137	77.97 140	77.12 106	55.40 177	57.87 147	46.68 169	56.17 137	60.39 129	62.36 115	76.32 157	76.25 156	85.35 150	81.34 136

diffmvs		74.86 80	77.37 76	71.93 84	75.62 133	80.35 111	79.42 82	60.15 146	72.81 68	64.63 79	71.51 57	73.11 73	66.53 97	79.02 126	77.98 128	85.25 151	86.83 77
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GA-MVS		68.14 136	69.17 137	66.93 146	73.77 154	78.50 132	74.45 132	58.28 165	55.11 171	48.44 158	60.08 111	53.99 166	61.50 129	78.43 133	77.57 135	85.13 152	80.54 144

v148		67.85 142	67.53 155	68.23 123	73.25 158	77.57 146	74.26 139	57.36 172	55.70 167	57.45 108	53.53 157	55.42 155	61.96 122	75.23 161	73.92 170	85.08 153	81.32 137

viewmambaseed2359dif		73.61 87	75.14 88	71.84 86	75.87 129	79.69 116	78.99 87	60.42 142	68.19 82	64.15 81	67.85 79	71.20 83	66.55 94	77.41 144	75.78 158	85.04 154	85.85 85

HyFIR lowres test		69.47 125	68.94 139	70.09 105	76.77 122	82.93 84	76.63 112	60.17 145	59.00 144	54.03 124	40.54 209	65.23 115	67.89 83	76.54 156	78.30 125	85.03 155	80.07 150

gg-mvs-nofinetune		62.55 177	65.05 175	59.62 185	78.72 105	77.61 144	70.83 164	53.63 179	39.71 218	22.04 220	36.36 213	64.32 117	47.53 190	81.16 92	79.03 115	85.00 156	77.17 169

COLMAP_ROB	62.73 15	67.66 146	66.76 163	68.70 120	80.49 89	77.98 138	75.29 118	62.95 103	63.62 114	49.96 149	47.32 194	50.72 193	58.57 143	76.87 151	75.50 163	84.94 157	75.33 183
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tfpnnormal		64.27 169	63.64 185	65.02 157	75.84 131	75.61 161	71.24 163	62.52 116	47.79 203	42.97 186	42.65 202	44.49 212	52.66 182	78.77 129	76.86 147	84.88 158	79.29 156

viewmsd2359difaftdt		72.49 94	74.10 94	70.61 95	75.87 129	78.53 131	76.92 107	58.16 166	65.69 97	61.33 92	67.21 82	68.34 105	66.51 98	77.91 138	75.60 160	84.86 159	85.42 94

pm-mvs1		65.62 160	67.42 157	63.53 168	73.66 156	76.39 154	69.66 166	60.87 136	49.73 199	43.97 183	51.24 180	57.00 149	48.16 189	79.89 113	77.84 130	84.85 160	79.82 152

gm-plane-assit		57.00 201	57.62 208	56.28 197	76.10 124	62.43 214	47.62 222	46.57 213	33.84 222	23.24 216	37.52 210	40.19 219	59.61 139	79.81 114	77.55 136	84.55 161	72.03 193

USDC		67.36 152	67.90 153	66.74 149	71.72 170	75.23 166	71.58 160	60.28 143	67.45 86	50.54 148	60.93 105	45.20 211	62.08 118	76.56 155	74.50 168	84.25 162	75.38 182

dmvs_re		67.22 154	67.92 152	66.40 151	75.94 128	70.55 185	74.97 128	63.87 89	57.07 156	44.75 180	54.29 149	56.72 150	54.65 174	79.53 119	77.51 137	84.20 163	79.78 153

MS-PatchMatch		70.17 117	70.49 121	69.79 108	80.98 84	77.97 140	77.51 101	58.95 160	62.33 123	55.22 119	53.14 164	65.90 113	62.03 120	79.08 125	77.11 145	84.08 164	77.91 164

TDRefinement		66.09 159	65.03 176	67.31 137	69.73 187	76.75 151	75.33 116	64.55 83	60.28 139	49.72 153	45.63 197	42.83 214	60.46 137	75.75 158	75.95 157	84.08 164	78.04 163

pmmvs4		67.89 141	67.39 159	68.48 122	71.60 174	73.57 173	74.45 132	60.98 134	64.65 103	57.97 105	54.95 146	51.73 188	61.88 123	73.78 170	75.11 164	83.99 166	77.91 164

pmmvs5		62.37 183	64.04 182	60.42 179	65.03 201	71.67 180	67.17 178	52.70 189	50.30 196	44.80 179	54.23 153	51.19 191	49.37 187	72.88 173	73.48 174	83.45 167	74.55 186

pmmvs-eth3d		63.52 172	62.44 194	64.77 159	66.82 198	70.12 186	69.41 168	59.48 154	54.34 180	52.71 134	46.24 196	44.35 213	56.93 158	72.37 174	73.77 172	83.30 168	75.91 176

pmmvs6		62.41 180	62.88 188	61.87 173	71.38 176	75.18 168	67.76 175	59.45 155	41.64 214	42.52 188	37.33 211	52.91 179	46.87 191	77.67 141	76.26 155	83.23 169	79.18 158

CDS-MVSNet		67.65 147	69.83 128	65.09 156	75.39 136	76.55 153	74.42 135	63.75 90	53.55 182	49.37 154	59.41 117	62.45 123	44.44 195	79.71 115	79.82 102	83.17 170	77.36 168
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PMMVS		65.06 164	69.17 137	60.26 181	55.25 222	63.43 208	66.71 183	43.01 217	62.41 122	50.64 146	69.44 68	67.04 109	63.29 110	74.36 167	73.54 173	82.68 171	73.99 190

SixPastTwentyTwo		61.84 187	62.45 193	61.12 177	69.20 191	72.20 177	62.03 202	57.40 170	46.54 207	38.03 198	57.14 134	41.72 216	58.12 147	69.67 198	71.58 181	81.94 172	78.30 162

IterMVS		66.36 158	68.30 149	64.10 163	69.48 190	74.61 170	73.41 153	50.79 198	57.30 155	48.28 160	60.64 108	59.92 134	60.85 136	74.14 168	72.66 177	81.80 173	78.82 160
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchMatch-RL		67.78 144	66.65 164	69.10 116	73.01 159	72.69 176	68.49 172	61.85 125	62.93 119	60.20 95	56.83 135	50.42 194	69.52 72	75.62 159	74.46 169	81.51 174	73.62 191

TinyColmap		62.84 175	61.03 200	64.96 158	69.61 188	71.69 179	68.48 173	59.76 152	55.41 168	47.69 164	47.33 193	34.20 223	62.76 114	74.52 165	72.59 178	81.44 175	71.47 194

EPNet_dtu		68.08 138	71.00 117	64.67 160	79.64 98	68.62 192	75.05 124	63.30 95	66.36 91	45.27 178	67.40 81	66.84 111	43.64 197	75.37 160	74.98 166	81.15 176	77.44 167
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		64.83 165	65.54 170	64.01 165	70.64 182	69.41 187	65.97 187	52.74 187	57.81 149	52.65 135	54.27 150	56.31 152	60.92 133	72.20 179	73.09 175	81.12 177	75.69 179

RPMNet		61.71 190	62.88 188	60.34 180	69.51 189	69.41 187	63.48 197	49.23 203	57.81 149	45.64 177	50.51 182	50.12 195	53.13 181	68.17 205	68.49 196	81.07 178	75.62 181

test-mter		60.84 192	64.62 179	56.42 196	55.99 220	64.18 203	65.39 189	34.23 222	54.39 179	46.21 173	57.40 133	59.49 136	55.86 166	71.02 189	69.65 187	80.87 179	76.20 175

test-LLR		64.42 167	64.36 180	64.49 161	75.02 139	63.93 205	66.61 184	61.96 123	54.41 177	47.77 162	57.46 131	60.25 130	55.20 172	70.80 190	69.33 188	80.40 180	74.38 187

TESTMET0.1,1		61.10 191	64.36 180	57.29 193	57.53 217	63.93 205	66.61 184	36.22 221	54.41 177	47.77 162	57.46 131	60.25 130	55.20 172	70.80 190	69.33 188	80.40 180	74.38 187

CostFormer		68.92 130	69.58 131	68.15 124	75.98 127	76.17 157	78.22 97	51.86 192	65.80 95	61.56 90	63.57 97	62.83 122	61.85 124	70.40 196	68.67 193	79.42 182	79.62 155

CVMVSNet		62.55 177	65.89 166	58.64 189	66.95 196	69.15 189	66.49 186	56.29 176	52.46 188	32.70 204	59.27 118	58.21 143	50.09 186	71.77 182	71.39 182	79.31 183	78.99 159

CHOSEN 1792x2688		69.20 128	69.26 135	69.13 115	76.86 121	78.93 123	77.27 105	60.12 147	61.86 127	54.42 120	42.54 203	61.61 126	66.91 90	78.55 132	78.14 127	79.23 184	83.23 121

PM-MVS		60.48 193	60.94 201	59.94 182	58.85 214	66.83 198	64.27 195	51.39 195	55.03 173	48.03 161	50.00 186	40.79 218	58.26 146	69.20 201	67.13 203	78.84 185	77.60 166

baseline		70.45 113	74.09 95	66.20 152	70.95 180	75.67 159	74.26 139	53.57 180	68.33 81	58.42 101	69.87 66	71.45 79	61.55 128	74.84 164	74.76 167	78.42 186	83.72 117

PatchT		61.97 185	64.04 182	59.55 186	60.49 211	67.40 195	56.54 212	48.65 207	56.69 158	52.65 135	51.10 181	52.14 186	60.92 133	72.20 179	73.09 175	78.03 187	75.69 179

RPSCF		67.64 148	71.25 116	63.43 169	61.86 209	70.73 183	67.26 177	50.86 197	74.20 61	58.91 97	67.49 80	69.33 94	64.10 107	71.41 183	68.45 197	77.61 188	77.17 169

MDTV_nov1_ep13_2view		60.16 194	60.51 202	59.75 183	65.39 200	69.05 190	68.00 174	48.29 209	51.99 190	45.95 175	48.01 192	49.64 199	53.39 179	68.83 202	66.52 204	77.47 189	69.55 200

MDTV_nov1_ep13		64.37 168	65.24 172	63.37 170	68.94 192	70.81 182	72.40 159	50.29 201	60.10 140	53.91 126	60.07 112	59.15 137	57.21 155	69.43 200	67.30 200	77.47 189	69.78 199

LTVRE_ROB	59.44 16	61.82 189	62.64 191	60.87 178	72.83 164	77.19 147	64.37 194	58.97 159	33.56 223	28.00 210	52.59 173	42.21 215	63.93 108	74.52 165	76.28 154	77.15 191	82.13 125
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
IterMVS-SCA-FT		66.89 157	69.22 136	64.17 162	71.30 178	75.64 160	71.33 161	53.17 184	57.63 153	49.08 156	60.72 107	60.05 133	63.09 111	74.99 163	73.92 170	77.07 192	81.57 135

SCA		65.40 162	66.58 165	64.02 164	70.65 181	73.37 174	67.35 176	53.46 182	63.66 113	54.14 122	60.84 106	60.20 132	61.50 129	69.96 197	68.14 198	77.01 193	69.91 197

MDA-MVSNet-bldmvs		53.37 210	53.01 213	53.79 205	43.67 226	67.95 194	59.69 208	57.92 168	43.69 210	32.41 205	41.47 204	27.89 229	52.38 183	56.97 221	65.99 206	76.68 194	67.13 204

MVS-HIRNet		54.41 207	52.10 214	57.11 195	58.99 213	56.10 220	49.68 220	49.10 204	46.18 208	52.15 139	33.18 217	46.11 208	56.10 163	63.19 213	59.70 216	76.64 195	60.25 216

dps		64.00 171	62.99 187	65.18 155	73.29 157	72.07 178	68.98 171	53.07 185	57.74 151	58.41 102	55.55 141	47.74 204	60.89 135	69.53 199	67.14 202	76.44 196	71.19 195

test0.0.03 1		58.80 197	61.58 198	55.56 199	75.02 139	68.45 193	59.58 209	61.96 123	52.74 185	29.57 207	49.75 187	54.56 161	31.46 213	71.19 185	69.77 186	75.75 197	64.57 208

EU-MVSNet		54.63 206	58.69 204	49.90 210	56.99 218	62.70 213	56.41 213	50.64 200	45.95 209	23.14 217	50.42 183	46.51 207	36.63 208	65.51 208	64.85 207	75.57 198	74.91 184

PatchmatchNet		64.21 170	64.65 178	63.69 166	71.29 179	68.66 191	69.63 167	51.70 194	63.04 117	53.77 127	59.83 115	58.34 142	60.23 138	68.54 203	66.06 205	75.56 199	68.08 203
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Anonymous20231206		56.36 203	57.80 207	54.67 202	70.08 184	66.39 199	60.46 206	57.54 169	49.50 201	29.30 208	33.86 216	46.64 206	35.18 209	70.44 194	68.88 192	75.47 200	68.88 202

CMPMVS	47.78 17	62.49 179	62.52 192	62.46 171	70.01 186	70.66 184	62.97 199	51.84 193	51.98 191	56.71 112	42.87 201	53.62 167	57.80 150	72.23 177	70.37 185	75.45 201	75.91 176
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MIMVSNet		58.52 199	61.34 199	55.22 200	60.76 210	67.01 197	66.81 181	49.02 205	56.43 161	38.90 194	40.59 208	54.54 162	40.57 204	73.16 172	71.65 180	75.30 202	66.00 206

TAMVS		59.58 196	62.81 190	55.81 198	66.03 199	65.64 202	63.86 196	48.74 206	49.95 198	37.07 200	54.77 147	58.54 140	44.44 195	72.29 176	71.79 179	74.70 203	66.66 205

tpm cat1		65.41 161	63.81 184	67.28 139	75.61 134	72.88 175	75.32 117	52.85 186	62.97 118	63.66 85	53.24 162	53.29 178	61.83 125	65.54 207	64.14 209	74.43 204	74.60 185

test20.03		53.93 209	56.28 210	51.19 208	72.19 167	65.83 200	53.20 216	61.08 130	42.74 212	22.08 219	37.07 212	45.76 210	24.29 221	70.44 194	69.04 190	74.31 205	63.05 212

FMVSNet5		57.24 200	60.02 203	53.99 204	56.45 219	62.74 212	65.27 190	47.03 212	55.14 170	39.55 193	40.88 206	53.42 175	41.83 198	72.35 175	71.10 184	73.79 206	64.50 209

testgi		54.39 208	57.86 206	50.35 209	71.59 175	67.24 196	54.95 214	53.25 183	43.36 211	23.78 215	44.64 198	47.87 203	24.96 218	70.45 193	68.66 194	73.60 207	62.78 213

MIMVSNet1		49.27 212	53.25 212	44.62 214	44.61 224	61.52 215	53.61 215	52.18 190	41.62 215	18.68 224	28.14 222	41.58 217	25.50 216	68.46 204	69.04 190	73.15 208	62.37 214

pmmvs3		47.65 213	49.08 218	45.99 213	44.61 224	54.79 221	50.04 218	31.95 225	33.91 221	29.90 206	30.37 218	33.53 224	46.31 192	63.50 211	63.67 210	73.14 209	63.77 211

FC-MVSNet-test		56.90 202	65.20 173	47.21 212	66.98 195	63.20 210	49.11 221	58.60 164	59.38 143	11.50 228	65.60 87	56.68 151	24.66 220	71.17 186	71.36 183	72.38 210	69.02 201

GG-mvs-BLEND		46.86 216	67.51 156	22.75 222	0.05 234	76.21 156	64.69 192	0.04 230	61.90 126	0.09 235	55.57 140	71.32 81	0.08 230	70.54 192	67.19 201	71.58 211	69.86 198

ambc			53.42 211		64.99 202	63.36 209	49.96 219		47.07 205	37.12 199	28.97 220	16.36 232	41.82 199	75.10 162	67.34 199	71.55 212	75.72 178

tpmrst		62.00 184	62.35 195	61.58 174	71.62 173	64.14 204	69.07 170	48.22 211	62.21 124	53.93 125	58.26 128	55.30 157	55.81 167	63.22 212	62.62 211	70.85 213	70.70 196

tpm		62.41 180	63.15 186	61.55 175	72.24 166	63.79 207	71.31 162	46.12 215	57.82 148	55.33 117	59.90 114	54.74 160	53.63 178	67.24 206	64.29 208	70.65 214	74.25 189

FPMVS		51.87 211	50.00 216	54.07 203	66.83 197	57.25 218	60.25 207	50.91 196	50.25 197	34.36 202	36.04 214	32.02 225	41.49 200	58.98 218	56.07 218	70.56 215	59.36 218

EPMVS		60.00 195	61.97 196	57.71 192	68.46 193	63.17 211	64.54 193	48.23 210	63.30 115	44.72 181	60.19 110	56.05 154	50.85 185	65.27 210	62.02 212	69.44 216	63.81 210

PMVS	39.38 18	46.06 217	43.30 220	49.28 211	62.93 205	38.75 226	41.88 224	53.50 181	33.33 224	35.46 201	28.90 221	31.01 226	33.04 212	58.61 220	54.63 221	68.86 217	57.88 219
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmnet_mix02		55.30 205	57.01 209	53.30 207	64.14 204	59.09 216	58.39 211	50.24 202	53.47 183	38.68 195	49.75 187	45.86 209	40.14 205	65.38 209	60.22 214	68.19 218	65.33 207

CHOSEN 280x420		58.70 198	61.88 197	54.98 201	55.45 221	50.55 224	64.92 191	40.36 218	55.21 169	38.13 197	48.31 190	63.76 119	63.03 113	73.73 171	68.58 195	68.00 219	73.04 192

new-patchmatchnet		46.97 215	49.47 217	44.05 216	62.82 206	56.55 219	45.35 223	52.01 191	42.47 213	17.04 226	35.73 215	35.21 222	21.84 224	61.27 215	54.83 220	65.26 220	60.26 215

ADS-MVSNet		55.94 204	58.01 205	53.54 206	62.48 208	58.48 217	59.12 210	46.20 214	59.65 142	42.88 187	52.34 175	53.31 177	46.31 192	62.00 214	60.02 215	64.23 221	60.24 217

N_pmnet		47.35 214	50.13 215	44.11 215	59.98 212	51.64 223	51.86 217	44.80 216	49.58 200	20.76 222	40.65 207	40.05 220	29.64 214	59.84 216	55.15 219	57.63 222	54.00 220

new_pmnet		38.40 219	42.64 221	33.44 219	37.54 229	45.00 225	36.60 225	32.72 224	40.27 216	12.72 227	29.89 219	28.90 227	24.78 219	53.17 222	52.90 222	56.31 223	48.34 221

Gipuma		36.38 220	35.80 222	37.07 217	45.76 223	33.90 227	29.81 226	48.47 208	39.91 217	18.02 225	8.00 230	8.14 234	25.14 217	59.29 217	61.02 213	55.19 224	40.31 223
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
WB-MVS		40.01 218	45.06 219	34.13 218	58.84 215	53.28 222	28.60 227	58.10 167	32.93 225	4.65 233	40.92 205	28.33 228	7.26 227	58.86 219	56.09 217	47.36 225	44.98 222

PMMVS2		25.60 221	29.75 223	20.76 223	28.00 230	30.93 228	23.10 229	29.18 226	23.14 227	1.46 234	18.23 226	16.54 231	5.08 228	40.22 223	41.40 224	37.76 226	37.79 225

test_method		22.26 222	25.94 224	17.95 224	3.24 233	7.17 233	23.83 228	7.27 228	37.35 220	20.44 223	21.87 225	39.16 221	18.67 225	34.56 224	20.84 228	34.28 227	20.64 229

E-PMN		21.77 223	18.24 226	25.89 220	40.22 227	19.58 230	12.46 232	39.87 219	18.68 229	6.71 230	9.57 227	4.31 237	22.36 223	19.89 228	27.28 226	33.73 228	28.34 227

EMVS		20.98 224	17.15 227	25.44 221	39.51 228	19.37 231	12.66 231	39.59 220	19.10 228	6.62 231	9.27 228	4.40 236	22.43 222	17.99 229	24.40 227	31.81 229	25.53 228

tmp_tt				14.50 226	14.68 231	7.17 233	10.46 234	2.21 229	37.73 219	28.71 209	25.26 223	16.98 230	4.37 229	31.49 225	29.77 225	26.56 230

MVE	19.12 19	20.47 225	23.27 225	17.20 225	12.66 232	25.41 229	10.52 233	34.14 223	14.79 230	6.53 232	8.79 229	4.68 235	16.64 226	29.49 226	41.63 223	22.73 231	38.11 224
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX						18.74 232	18.55 230	8.02 227	26.96 226	7.33 229	23.81 224	13.05 233	25.99 215	25.17 227		22.45 232	36.25 226

testmvs		0.09 226	0.15 228	0.02 227	0.01 235	0.02 235	0.05 236	0.01 231	0.11 231	0.01 236	0.26 232	0.01 238	0.06 232	0.10 230	0.10 229	0.01 233	0.43 231

test123		0.09 226	0.14 229	0.02 227	0.00 236	0.02 235	0.02 237	0.01 231	0.09 232	0.00 237	0.30 231	0.00 239	0.08 230	0.03 231	0.09 230	0.01 233	0.45 230

uanet_test		0.00 228	0.00 230	0.00 229	0.00 236	0.00 237	0.00 238	0.00 233	0.00 233	0.00 237	0.00 233	0.00 239	0.00 233	0.00 232	0.00 231	0.00 235	0.00 232

sosnet-low-res		0.00 228	0.00 230	0.00 229	0.00 236	0.00 237	0.00 238	0.00 233	0.00 233	0.00 237	0.00 233	0.00 239	0.00 233	0.00 232	0.00 231	0.00 235	0.00 232

sosnet		0.00 228	0.00 230	0.00 229	0.00 236	0.00 237	0.00 238	0.00 233	0.00 233	0.00 237	0.00 233	0.00 239	0.00 233	0.00 232	0.00 231	0.00 235	0.00 232

RE-MVS-def										46.24 172

9.14												86.88 16

SR-MVS					88.99 34			73.57 24				87.54 14

our_test_3					67.93 194	70.99 181	66.89 180

MTAPA										83.48 1		86.45 19

MTMP										82.66 5		84.91 27

Patchmatch-RL test							2.85 235

mPP-MVS					89.90 25							81.29 42

NP-MVS									80.10 47

Patchmtry						65.80 201	65.97 187	52.74 187		52.65 135

High-resolution multi-view benchmark