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.

SF-MVS		87.30 6	88.71 6	85.64 3	94.57 1	94.55 4	91.01 1	79.94 1	89.15 12	79.85 7	92.37 3	83.29 11	79.75 9	83.52 26	82.72 33	88.75 21	95.37 24

TPM-MVS					94.34 2	93.91 5	89.34 3			75.49 18	82.52 20	83.34 10	83.53 4			89.62 7	90.78 77
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
MCST-MVS		85.75 9	86.99 13	84.31 6	94.07 3	92.80 9	88.15 9	79.10 2	85.66 22	70.72 30	76.50 34	80.45 23	82.17 5	88.35 2	87.49 3	91.63 2	97.65 4

HPM-MVS++		85.64 10	88.43 7	82.39 12	92.65 4	90.24 26	85.83 17	74.21 11	90.68 9	75.63 17	86.77 13	84.15 8	78.68 16	86.33 8	85.26 10	87.32 60	95.60 18

CNVR-MVS		85.96 8	87.58 11	84.06 8	92.58 5	92.40 12	87.62 11	77.77 4	88.44 14	75.93 16	79.49 26	81.97 18	81.65 6	87.04 6	86.58 4	88.79 19	97.18 7

DVP-MVS++		87.98 3	89.76 5	85.89 2	92.57 6	94.57 3	88.34 6	76.61 7	92.40 6	83.40 3	89.26 10	85.57 5	86.04 2	86.24 11	84.89 15	88.39 32	95.42 21

SED-MVS		88.94 1	90.98 1	86.56 1	92.53 7	95.09 1	88.55 5	76.83 6	94.16 1	86.57 1	90.85 5	87.07 1	86.18 1	86.36 7	85.08 13	88.67 22	98.21 3

NCCC		84.16 16	85.46 22	82.64 11	92.34 8	90.57 23	86.57 14	76.51 8	86.85 19	72.91 24	77.20 32	78.69 27	79.09 15	84.64 20	84.88 16	88.44 30	95.41 22

DPE-MVS		87.60 5	90.44 4	84.29 7	92.09 9	93.44 6	88.69 4	75.11 9	93.06 5	80.80 6	94.23 2	86.70 3	81.44 7	84.84 18	83.52 27	87.64 51	97.28 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		88.07 2	90.73 2	84.97 4	91.98 10	95.01 2	87.86 10	76.88 5	93.90 2	85.15 2	90.11 7	86.90 2	79.46 12	86.26 10	84.67 18	88.50 29	98.25 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
CSCG		82.90 21	84.52 24	81.02 18	91.85 11	93.43 7	87.14 12	74.01 14	81.96 32	76.14 14	70.84 38	82.49 14	69.71 67	82.32 41	85.18 12	87.26 64	95.40 23

SMA-MVS		85.24 12	88.27 9	81.72 15	91.74 12	90.71 20	86.71 13	73.16 19	90.56 10	74.33 20	83.07 18	85.88 4	77.16 21	86.28 9	85.58 7	87.23 65	95.77 14
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
DPM-MVS		85.41 11	86.72 17	83.89 10	91.66 13	91.92 15	90.49 2	78.09 3	86.90 18	73.95 21	74.52 36	82.01 17	79.29 13	90.24 1	90.65 1	89.86 6	90.78 77

QAPM		77.50 45	77.43 53	77.59 35	91.52 14	92.00 14	81.41 40	70.63 27	66.22 76	58.05 76	54.70 86	71.79 44	74.49 33	82.46 37	82.04 37	89.46 14	92.79 56

APDe-MVS		86.37 7	88.41 8	84.00 9	91.43 15	91.83 16	88.34 6	74.67 10	91.19 7	81.76 5	91.13 4	81.94 19	80.07 8	83.38 27	82.58 35	87.69 49	96.78 11
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
3Dnovator	70.49 5	78.42 38	76.77 59	80.35 20	91.43 15	90.27 25	81.84 37	70.79 26	72.10 60	71.95 25	50.02 105	67.86 57	77.47 20	82.89 32	84.24 20	88.61 25	89.99 88

DeepC-MVS_fast	75.41 2	81.69 25	82.10 32	81.20 17	91.04 17	87.81 54	83.42 27	74.04 13	83.77 26	71.09 28	66.88 49	72.44 38	79.48 11	85.08 15	84.97 14	88.12 40	93.78 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SteuartSystems-ACMMP		82.51 22	85.35 23	79.20 26	90.25 18	89.39 34	84.79 22	70.95 25	82.86 28	68.32 38	86.44 14	77.19 28	73.07 40	83.63 25	83.64 24	87.82 44	94.34 32
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		82.48 23	84.12 25	80.56 19	90.15 19	87.55 55	84.28 24	69.67 32	85.22 23	77.95 13	84.69 16	75.94 31	75.04 27	81.85 49	81.17 55	86.30 88	92.40 58

DeepPCF-MVS	76.94 1	83.08 20	87.77 10	77.60 34	90.11 20	90.96 19	78.48 57	72.63 22	93.10 4	65.84 43	80.67 24	81.55 20	74.80 29	85.94 13	85.39 9	83.75 150	96.77 12

OpenMVS	67.62 8	74.92 62	73.91 75	76.09 42	90.10 21	90.38 24	78.01 61	66.35 54	66.09 79	62.80 52	46.33 130	64.55 69	71.77 52	79.92 66	80.88 61	87.52 55	89.20 97

MAR-MVS		77.19 48	78.37 50	75.81 44	89.87 22	90.58 22	79.33 55	65.56 60	77.62 50	58.33 75	59.24 73	67.98 55	74.83 28	82.37 40	83.12 29	86.95 72	87.67 113
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
TSAR-MVS + ACMM		81.59 26	85.84 21	76.63 38	89.82 23	86.53 70	86.32 16	66.72 52	85.96 21	65.43 44	88.98 11	82.29 15	67.57 85	82.06 46	81.33 52	83.93 148	93.75 43

train_agg		83.35 19	86.93 15	79.17 27	89.70 24	88.41 44	85.60 20	72.89 21	86.31 20	66.58 42	90.48 6	82.24 16	73.06 41	83.10 31	82.64 34	87.21 69	95.30 25

APD-MVS		84.83 13	87.00 12	82.30 13	89.61 25	89.21 36	86.51 15	73.64 16	90.98 8	77.99 12	89.89 8	80.04 25	79.18 14	82.00 48	81.37 51	86.88 74	95.49 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ACMMP_NAP		83.54 18	86.37 19	80.25 22	89.57 26	90.10 28	85.27 21	71.66 23	87.38 16	73.08 23	84.23 17	80.16 24	75.31 25	84.85 17	83.64 24	86.57 81	94.21 35

MSP-MVS		87.87 4	90.57 3	84.73 5	89.38 27	91.60 17	88.24 8	74.15 12	93.55 3	82.28 4	94.99 1	83.21 12	85.96 3	87.67 4	84.67 18	88.32 33	98.29 1
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
AdaColmap		76.23 53	73.55 77	79.35 25	89.38 27	85.00 86	79.99 52	73.04 20	76.60 52	71.17 27	55.18 85	57.99 105	77.87 18	76.82 97	76.82 100	84.67 135	86.45 120

3Dnovator+	70.16 6	77.87 41	77.29 55	78.55 29	89.25 29	88.32 46	80.09 50	67.95 43	74.89 58	71.83 26	52.05 98	70.68 48	76.27 24	82.27 42	82.04 37	85.92 96	90.77 79

CDPH-MVS		79.39 35	82.13 31	76.19 41	89.22 30	88.34 45	84.20 25	71.00 24	79.67 44	56.97 81	77.77 29	72.24 42	68.50 79	81.33 52	82.74 30	87.23 65	92.84 54

SD-MVS		84.31 15	86.96 14	81.22 16	88.98 31	88.68 41	85.65 18	73.85 15	89.09 13	79.63 8	87.34 12	84.84 6	73.71 35	82.66 35	81.60 48	85.48 113	94.51 30
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
MVS_0304		83.82 17	86.88 16	80.26 21	88.48 32	93.17 8	82.93 32	67.66 45	88.28 15	74.90 19	77.08 33	80.93 21	78.09 17	85.83 14	85.88 6	89.53 10	96.96 10

MP-MVS		80.94 27	83.49 27	77.96 31	88.48 32	88.16 48	82.82 33	69.34 34	80.79 38	69.67 34	82.35 21	77.13 29	71.60 54	80.97 58	80.96 59	85.87 99	94.06 38
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMPR		80.62 29	82.98 28	77.87 33	88.41 34	87.05 62	83.02 29	69.18 35	83.91 25	68.35 37	82.89 19	73.64 35	72.16 48	80.78 59	81.13 56	86.10 93	91.43 67

MSLP-MVS++		78.57 37	77.33 54	80.02 23	88.39 35	84.79 87	84.62 23	66.17 56	75.96 53	78.40 10	61.59 63	71.47 45	73.54 38	78.43 80	78.88 80	88.97 17	90.18 87

PGM-MVS		79.42 34	81.84 33	76.60 39	88.38 36	86.69 66	82.97 31	65.75 58	80.39 39	64.94 45	81.95 23	72.11 43	71.41 57	80.45 60	80.55 66	86.18 90	90.76 80

EPNet		79.28 36	82.25 30	75.83 43	88.31 37	90.14 27	79.43 54	68.07 42	81.76 34	61.26 63	77.26 31	70.08 50	70.06 65	82.43 39	82.00 39	87.82 44	92.09 61
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DELS-MVS		79.49 31	79.84 40	79.08 28	88.26 38	92.49 10	84.12 26	70.63 27	65.27 84	69.60 36	61.29 65	66.50 60	72.75 44	88.07 3	88.03 2	89.13 15	97.22 6
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
TSAR-MVS + MP.		84.39 14	86.58 18	81.83 14	88.09 39	86.47 71	85.63 19	73.62 17	90.13 11	79.24 9	89.67 9	82.99 13	77.72 19	81.22 53	80.92 60	86.68 79	94.66 29
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
X-MVS		78.16 40	80.55 37	75.38 47	87.99 40	86.27 76	81.05 45	68.98 36	78.33 46	61.07 66	75.25 35	72.27 39	67.52 86	80.03 64	80.52 67	85.66 110	91.20 71

DeepC-MVS	74.46 3	80.30 30	81.05 35	79.42 24	87.42 41	88.50 43	83.23 28	73.27 18	82.78 29	71.01 29	62.86 60	69.93 51	74.80 29	84.30 21	84.20 21	86.79 77	94.77 27
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
mPP-MVS					86.96 42							70.61 49

CP-MVS		79.44 32	81.51 34	77.02 37	86.95 43	85.96 81	82.00 35	68.44 41	81.82 33	67.39 39	77.43 30	73.68 34	71.62 53	79.56 71	79.58 74	85.73 103	92.51 57

MVS_111021_HR		77.42 46	78.40 49	76.28 40	86.95 43	90.68 21	77.41 67	70.56 30	66.21 78	62.48 56	66.17 52	63.98 71	72.08 49	82.87 33	83.15 28	88.24 36	95.71 16

CANet		80.90 28	82.93 29	78.53 30	86.83 45	92.26 13	81.19 43	66.95 49	81.60 35	69.90 33	66.93 48	74.80 32	76.79 22	84.68 19	84.77 17	89.50 12	95.50 19

CHOSEN 1792x2688		72.55 75	71.98 85	73.22 61	86.57 46	92.41 11	75.63 75	66.77 51	62.08 93	52.32 94	30.27 199	50.74 138	66.14 89	86.22 12	85.41 8	91.90 1	96.75 13

SR-MVS					86.33 47			67.54 46				80.78 22

PHI-MVS		79.43 33	84.06 26	74.04 57	86.15 48	91.57 18	80.85 47	68.90 38	82.22 31	51.81 97	78.10 28	74.28 33	70.39 64	84.01 24	84.00 22	86.14 92	94.24 33

ACMMP		77.61 44	79.59 41	75.30 48	85.87 49	85.58 82	81.42 39	67.38 48	79.38 45	62.61 54	78.53 27	65.79 62	68.80 78	78.56 79	78.50 85	85.75 100	90.80 76
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
HQP-MVS		78.26 39	80.91 36	75.17 49	85.67 50	84.33 93	83.01 30	69.38 33	79.88 42	55.83 82	79.85 25	64.90 67	70.81 59	82.46 37	81.78 43	86.30 88	93.18 49

OPM-MVS		72.74 74	70.93 95	74.85 53	85.30 51	84.34 92	82.82 33	69.79 31	49.96 144	55.39 88	54.09 93	60.14 91	70.04 66	80.38 62	79.43 75	85.74 102	88.20 109
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MS-PatchMatch		70.34 90	69.00 106	71.91 73	85.20 52	85.35 83	77.84 63	61.77 97	58.01 111	55.40 87	41.26 149	58.34 102	61.69 113	81.70 51	78.29 86	89.56 9	80.02 167

PCF-MVS	70.85 4	75.73 56	76.55 62	74.78 54	83.67 53	88.04 52	81.47 38	70.62 29	69.24 71	57.52 79	60.59 69	69.18 53	70.65 61	77.11 94	77.65 94	84.75 133	94.01 39
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMM	66.70 10	70.42 86	68.49 110	72.67 65	82.85 54	77.76 150	77.70 65	64.76 65	64.61 85	60.74 70	49.29 107	53.97 128	65.86 90	74.97 115	75.57 116	84.13 147	83.29 149
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVS					82.43 55	86.27 76	75.70 73			61.07 66		72.27 39				85.67 107

X-MVStestdata					82.43 55	86.27 76	75.70 73			61.07 66		72.27 39				85.67 107

PVSNet_BlendedMVS		76.84 50	78.47 47	74.95 51	82.37 57	89.90 30	75.45 79	65.45 61	74.99 56	70.66 31	63.07 58	58.27 103	67.60 83	84.24 22	81.70 45	88.18 37	97.10 8

PVSNet_Blended		76.84 50	78.47 47	74.95 51	82.37 57	89.90 30	75.45 79	65.45 61	74.99 56	70.66 31	63.07 58	58.27 103	67.60 83	84.24 22	81.70 45	88.18 37	97.10 8

CLD-MVS		77.36 47	77.29 55	77.45 36	82.21 59	88.11 49	81.92 36	68.96 37	77.97 48	69.62 35	62.08 61	59.44 95	73.57 37	81.75 50	81.27 53	88.41 31	90.39 84
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LGP-MVS_train		72.02 79	73.18 80	70.67 80	82.13 60	80.26 127	79.58 53	63.04 78	70.09 65	51.98 95	65.06 53	55.62 118	62.49 110	75.97 106	76.32 107	84.80 132	88.93 100

MSDG		65.57 122	61.57 159	70.24 82	82.02 61	76.47 159	74.46 92	68.73 40	56.52 116	50.33 105	38.47 164	41.10 163	62.42 111	72.12 149	72.94 150	83.47 153	73.37 189

IB-MVS	64.48 11	69.02 96	68.97 107	69.09 91	81.75 62	89.01 38	64.50 157	64.91 64	56.65 115	62.59 55	47.89 114	45.23 151	51.99 161	69.18 176	81.88 42	88.77 20	92.93 52
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
sasdasda		77.65 42	79.59 41	75.39 45	81.52 63	89.83 32	81.32 41	60.74 109	80.05 40	66.72 40	68.43 42	65.09 63	74.72 31	78.87 75	82.73 31	87.32 60	92.16 59

canonicalmvs		77.65 42	79.59 41	75.39 45	81.52 63	89.83 32	81.32 41	60.74 109	80.05 40	66.72 40	68.43 42	65.09 63	74.72 31	78.87 75	82.73 31	87.32 60	92.16 59

CPTT-MVS		75.43 58	77.13 57	73.44 59	81.43 65	82.55 105	80.96 46	64.35 66	77.95 49	61.39 62	69.20 41	70.94 47	69.38 74	73.89 129	73.32 143	83.14 160	92.06 62

EPNet_dtu		66.17 118	70.13 101	61.54 148	81.04 66	77.39 154	68.87 135	62.50 89	69.78 66	33.51 185	63.77 57	56.22 113	37.65 198	72.20 148	72.18 158	85.69 106	79.38 169
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMP	68.86 7	72.15 78	72.25 83	72.03 71	80.96 67	80.87 121	77.93 62	64.13 68	69.29 69	60.79 69	64.04 56	53.54 130	63.91 100	73.74 132	75.27 119	84.45 140	88.98 99
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HyFIR lowres test		68.39 101	68.28 113	68.52 95	80.85 68	88.11 49	71.08 119	58.09 125	54.87 131	47.80 116	27.55 205	55.80 116	64.97 93	79.11 73	79.14 78	88.31 34	93.35 46

LS3D		64.54 131	62.14 155	67.34 107	80.85 68	75.79 165	69.99 126	65.87 57	60.77 97	44.35 129	42.43 143	45.95 150	65.01 92	69.88 171	68.69 181	77.97 198	71.43 196

CNLPA		71.37 84	70.27 100	72.66 66	80.79 70	81.33 115	71.07 120	65.75 58	82.36 30	64.80 46	42.46 142	56.49 111	72.70 45	73.00 140	70.52 174	80.84 183	85.76 130

TSAR-MVS + GP.		82.27 24	85.98 20	77.94 32	80.72 71	88.25 47	81.12 44	67.71 44	87.10 17	73.31 22	85.23 15	83.68 9	76.64 23	80.43 61	81.47 50	88.15 39	95.66 17

MGCFI-Net		74.26 65	78.69 45	69.10 89	80.64 72	87.32 57	73.21 98	59.20 118	79.76 43	50.18 107	68.10 44	64.86 68	64.65 97	78.28 84	80.83 62	86.69 78	91.69 66

baseline1		71.47 81	72.02 84	70.82 78	80.56 73	84.51 89	76.61 72	66.93 50	56.22 119	48.66 111	55.40 84	60.43 88	62.55 109	83.35 29	80.99 57	89.60 8	83.28 150

casdiffmvs_mvg		75.57 57	76.04 64	75.02 50	80.48 74	89.31 35	80.79 48	64.04 70	66.95 74	63.87 48	57.52 76	61.33 84	72.90 42	82.01 47	81.99 40	88.03 41	93.16 50
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PLC	64.00 12	68.54 99	66.66 124	70.74 79	80.28 75	74.88 171	72.64 101	63.70 73	69.26 70	55.71 84	47.24 121	55.31 120	70.42 63	72.05 151	70.67 172	81.66 177	77.19 175
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
OMC-MVS		74.03 67	75.82 66	71.95 72	79.56 76	80.98 119	75.35 81	63.21 76	84.48 24	61.83 59	61.54 64	66.89 58	69.41 73	76.60 99	74.07 133	82.34 170	86.15 124

CostFormer		72.18 77	73.90 76	70.18 83	79.47 77	86.19 79	76.94 71	48.62 187	66.07 80	60.40 71	54.14 92	65.82 61	67.98 80	75.84 107	76.41 105	87.67 50	92.83 55

MVS_111021_LR		74.26 65	75.95 65	72.27 69	79.43 78	85.04 85	72.71 100	65.27 63	70.92 63	63.58 50	69.32 40	60.31 90	69.43 72	77.01 95	77.15 97	83.22 157	91.93 64

viewmanbaseed2359cas		74.53 63	74.69 73	74.35 56	79.37 79	88.90 39	78.96 56	64.07 69	63.67 86	62.19 57	56.95 78	58.42 101	72.04 50	80.08 63	81.92 41	89.47 13	92.91 53

MVS_Test		75.22 59	76.69 60	73.51 58	79.30 80	88.82 40	80.06 51	58.74 120	69.77 67	57.50 80	59.78 72	61.35 82	75.31 25	82.07 45	83.60 26	90.13 5	91.41 69

SPE-MVS-test		75.09 61	77.84 51	71.87 74	79.27 81	86.92 63	70.53 125	60.36 113	75.13 55	63.13 51	67.92 45	65.08 65	71.43 55	78.15 86	78.51 84	86.53 83	93.16 50

casdiffmvs		75.20 60	75.69 67	74.63 55	79.26 82	89.07 37	78.47 58	63.59 74	67.05 73	63.79 49	55.72 83	60.32 89	73.58 36	82.16 43	81.78 43	89.08 16	93.72 44
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS		75.84 55	78.61 46	72.61 67	79.03 83	86.74 65	74.43 93	60.27 115	74.15 59	62.78 53	66.26 51	64.25 70	72.81 43	83.36 28	81.69 47	86.32 86	93.85 41

PVSNet_Blended_VisFu		71.76 80	73.54 78	69.69 84	79.01 84	87.16 60	72.05 104	61.80 96	56.46 117	59.66 72	53.88 94	62.48 74	59.08 133	81.17 54	78.90 79	86.53 83	94.74 28

ACMH	59.42 14	61.59 156	59.22 175	64.36 125	78.92 85	78.26 144	67.65 141	67.48 47	39.81 185	30.98 192	38.25 166	34.59 195	61.37 117	70.55 165	73.47 139	79.74 190	79.59 168
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EC-MVSNet		76.05 54	78.87 44	72.77 64	78.87 86	86.63 67	77.50 66	57.04 141	75.34 54	61.68 61	64.20 55	69.56 52	73.96 34	82.12 44	80.65 64	87.57 53	93.57 45

test2506		69.26 92	70.79 96	67.48 105	78.64 87	86.40 73	72.22 102	62.75 87	58.05 109	45.24 123	50.76 101	54.93 122	58.05 139	79.82 67	79.70 70	87.96 42	85.90 128

ECVR-MVS		67.93 106	68.49 110	67.28 108	78.64 87	86.40 73	72.22 102	62.75 87	58.05 109	44.06 131	40.92 153	48.20 143	58.05 139	79.82 67	79.70 70	87.96 42	86.32 123

FC-MVSNet-train		68.83 98	68.29 112	69.47 85	78.35 89	79.94 128	64.72 156	66.38 53	54.96 128	54.51 91	56.75 79	47.91 145	66.91 87	75.57 112	75.75 112	85.92 96	87.12 115

ETV-MVS		76.25 52	80.22 38	71.63 75	78.23 90	87.95 53	72.75 99	60.27 115	77.50 51	57.73 77	71.53 37	66.60 59	73.16 39	80.99 57	81.23 54	87.63 52	95.73 15

EIA-MVS		73.48 70	76.05 63	70.47 81	78.12 91	87.21 59	71.78 107	60.63 111	69.66 68	55.56 86	64.86 54	60.69 86	69.53 70	77.35 93	78.59 81	87.22 67	94.01 39

Effi-MVS+		70.42 86	71.23 92	69.47 85	78.04 92	85.24 84	75.57 77	58.88 119	59.56 102	48.47 112	52.73 97	54.94 121	69.69 68	78.34 82	77.06 98	86.18 90	90.73 81

Anonymous202405211			66.35 128		78.00 93	84.41 91	74.85 83	63.18 77	51.00 140		31.37 196	53.73 129	69.67 69	76.28 101	76.84 99	83.21 159	90.85 75

thres100view900		67.14 115	66.09 130	68.38 98	77.70 94	83.84 97	74.52 89	66.33 55	49.16 148	43.40 135	43.24 134	41.34 159	62.59 108	79.31 72	75.92 111	85.73 103	89.81 89

tfpn200view9		65.90 120	64.96 134	67.00 109	77.70 94	81.58 111	71.71 110	62.94 83	49.16 148	43.40 135	43.24 134	41.34 159	61.42 115	76.24 102	74.63 125	84.84 128	88.52 106

DCV-MVSNet		69.13 95	69.07 105	69.21 87	77.65 96	77.52 152	74.68 84	57.85 130	54.92 129	55.34 89	55.74 82	55.56 119	66.35 88	75.05 114	76.56 103	83.35 154	88.13 110

Anonymous20231211		68.44 100	66.37 127	70.86 77	77.58 97	83.49 98	75.15 82	61.89 94	52.54 137	58.50 74	28.89 201	56.78 110	69.29 75	74.96 117	76.61 101	82.73 163	91.36 70

UA-Net		64.62 128	68.23 114	60.42 153	77.53 98	81.38 114	60.08 181	57.47 136	47.01 155	44.75 127	60.68 67	71.32 46	41.84 192	73.27 135	72.25 157	80.83 184	71.68 194

FA-MVS(training)		70.24 91	71.77 88	68.45 96	77.52 99	86.03 80	73.33 96	49.12 186	63.55 88	55.77 83	48.91 110	56.26 112	67.78 82	77.60 88	79.62 73	87.19 70	90.40 83

thres200		65.58 121	64.74 136	66.56 110	77.52 99	81.61 109	73.44 95	62.95 81	46.23 160	42.45 142	42.76 136	41.18 161	58.12 137	76.24 102	75.59 115	84.89 126	89.58 92

test1111		66.72 116	67.80 116	65.45 114	77.42 101	86.63 67	69.69 129	62.98 79	55.29 125	39.47 154	40.12 158	47.11 146	55.70 151	79.96 65	80.00 68	87.47 56	85.49 133

ACMH+	60.36 13	61.16 157	58.38 177	64.42 124	77.37 102	74.35 176	68.45 136	62.81 85	45.86 162	38.48 161	35.71 182	37.35 179	59.81 126	67.24 181	69.80 178	79.58 191	78.32 173

TAPA-MVS	67.10 9	71.45 82	73.47 79	69.10 89	77.04 103	80.78 122	73.81 94	62.10 91	80.80 37	51.28 98	60.91 66	63.80 73	67.98 80	74.59 119	72.42 155	82.37 169	80.97 164
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
IS_MVSNet		67.29 113	71.98 85	61.82 146	76.92 104	84.32 94	65.90 155	58.22 123	55.75 123	39.22 157	54.51 89	62.47 75	45.99 182	78.83 77	78.52 83	84.70 134	89.47 94

CANet_DTU		72.84 73	76.63 61	68.43 97	76.81 105	86.62 69	75.54 78	54.71 167	72.06 61	43.54 133	67.11 47	58.46 99	72.40 46	81.13 56	80.82 63	87.57 53	90.21 86

tpm cat1		67.47 111	67.05 122	67.98 100	76.63 106	81.51 113	74.49 91	47.65 192	61.18 95	61.12 64	42.51 141	53.02 133	64.74 96	70.11 170	71.50 161	83.22 157	89.49 93

GeoE		68.96 97	69.32 103	68.54 94	76.61 107	83.12 100	71.78 107	56.87 143	60.21 100	54.86 90	45.95 131	54.79 124	64.27 98	74.59 119	75.54 117	86.84 76	91.01 74

DI_MVS_pp		73.94 68	74.85 70	72.88 63	76.57 108	86.80 64	80.41 49	61.47 100	62.35 92	59.44 73	47.91 113	68.12 54	72.24 47	82.84 34	81.50 49	87.15 71	94.42 31

thres400		65.18 126	64.44 138	66.04 111	76.40 109	82.63 103	71.52 112	64.27 67	44.93 166	40.69 151	41.86 146	40.79 165	58.12 137	77.67 87	74.64 124	85.26 116	88.56 105

tpmrst		67.15 114	68.12 115	66.03 112	76.21 110	80.98 119	71.27 114	45.05 198	60.69 98	50.63 103	46.95 126	54.15 127	65.30 91	71.80 153	71.77 159	87.72 47	90.48 82

gg-mvs-nofinetune		62.34 145	66.19 129	57.86 169	76.15 111	88.61 42	71.18 117	41.24 215	25.74 217	13.16 220	22.91 213	63.97 72	54.52 156	85.06 16	85.25 11	90.92 3	91.78 65

baseline		72.89 72	74.46 74	71.07 76	75.99 112	87.50 56	74.57 85	60.49 112	70.72 64	57.60 78	60.63 68	60.97 85	70.79 60	75.27 113	76.33 106	86.94 73	89.79 91

EPMVS		66.21 117	67.49 119	64.73 120	75.81 113	84.20 95	68.94 134	44.37 202	61.55 94	48.07 115	49.21 109	54.87 123	62.88 106	71.82 152	71.40 165	88.28 35	79.37 170

baseline2		71.22 85	73.01 81	69.13 88	75.76 114	86.34 75	71.23 115	62.78 86	62.62 89	52.85 93	57.32 77	54.31 125	63.27 105	79.74 69	79.31 76	88.89 18	91.43 67

EPP-MVSNet		67.58 109	71.10 93	63.48 132	75.71 115	83.35 99	66.85 148	57.83 131	53.02 136	41.15 148	55.82 81	67.89 56	56.01 150	74.40 122	72.92 151	83.33 155	90.30 85

diffmvs		74.32 64	75.42 68	73.04 62	75.60 116	87.27 58	78.20 59	62.96 80	68.66 72	61.89 58	59.79 71	59.84 92	71.80 51	78.30 83	79.87 69	87.80 46	94.23 34
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
thres600view7		63.77 136	63.14 144	64.51 122	75.49 117	81.61 109	69.59 130	62.95 81	43.96 169	38.90 159	41.09 150	40.24 170	55.25 154	76.24 102	71.54 160	84.89 126	87.30 114

dps		64.08 133	63.22 143	65.08 117	75.27 118	79.65 131	66.68 150	46.63 196	56.94 113	55.67 85	43.96 133	43.63 156	64.00 99	69.50 175	69.82 176	82.25 171	79.02 171

diffmvs_AUTHOR		73.73 69	74.73 71	72.56 68	75.05 119	87.15 61	77.82 64	62.29 90	66.22 76	61.10 65	57.92 74	59.72 93	71.43 55	78.25 85	79.68 72	87.71 48	94.17 36

MVSTER		76.92 49	79.92 39	73.42 60	74.98 120	82.97 101	78.15 60	63.41 75	78.02 47	64.41 47	67.54 46	72.80 37	71.05 58	83.29 30	83.73 23	88.53 28	91.12 72

TSAR-MVS + COLMAP		73.09 71	76.86 58	68.71 92	74.97 121	82.49 106	74.51 90	61.83 95	83.16 27	49.31 110	82.22 22	51.62 135	68.94 77	78.76 78	75.52 118	82.67 165	84.23 142

viewmambaseed2359dif		72.54 76	72.88 82	72.13 70	74.78 122	86.45 72	77.24 69	61.65 99	62.61 90	61.83 59	55.85 80	57.51 108	70.64 62	75.71 108	77.90 93	86.65 80	94.16 37

tpm		64.85 127	66.02 131	63.48 132	74.52 123	78.38 143	70.98 121	44.99 200	51.61 139	43.28 137	47.66 116	53.18 131	60.57 120	70.58 164	71.30 168	86.54 82	89.45 95

dmvs_re		67.60 107	67.21 121	68.06 99	74.07 124	79.01 136	73.31 97	68.74 39	58.27 107	42.07 144	49.72 106	43.96 154	60.66 119	76.79 98	78.04 92	89.51 11	84.69 137

SCA		63.90 135	66.67 123	60.66 151	73.75 125	71.78 186	59.87 182	43.66 203	61.13 96	45.03 125	51.64 99	59.45 94	57.92 141	70.96 159	70.80 170	83.71 151	80.92 165

Vis-MVSNet (Re-imp)		62.25 148	68.74 108	54.68 184	73.70 126	78.74 139	56.51 190	57.49 135	55.22 126	26.86 198	54.56 88	61.35 82	31.06 200	73.10 137	74.90 121	82.49 167	83.31 148

Fast-Effi-MVS+		67.59 108	67.56 118	67.62 103	73.67 127	81.14 118	71.12 118	54.79 166	58.88 104	50.61 104	46.70 128	47.05 147	69.12 76	76.06 105	76.44 104	86.43 85	86.65 118

IterMVS-LS		66.08 119	66.56 126	65.51 113	73.67 127	74.88 171	70.89 122	53.55 173	50.42 142	48.32 114	50.59 103	55.66 117	61.83 112	73.93 128	74.42 129	84.82 131	86.01 126
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchmatchNet		65.43 124	67.71 117	62.78 138	73.49 129	82.83 102	66.42 153	45.40 197	60.40 99	45.27 122	49.22 108	57.60 107	60.01 125	70.61 162	71.38 166	86.08 94	81.91 161
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
COLMAP_ROB	51.17 15	55.13 183	52.90 196	57.73 171	73.47 130	67.21 199	62.13 173	55.82 150	47.83 152	34.39 181	31.60 195	34.24 196	44.90 186	63.88 195	62.52 203	75.67 203	63.02 212
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Effi-MVS+-dtu		64.58 129	64.08 139	65.16 116	73.04 131	75.17 170	70.68 124	56.23 147	54.12 134	44.71 128	47.42 117	51.10 136	63.82 101	68.08 179	66.32 190	82.47 168	86.38 121

thisisatest0530		68.38 102	70.98 94	65.35 115	72.61 132	84.42 90	68.21 138	57.98 126	59.77 101	50.80 102	54.63 87	58.48 98	57.92 141	76.99 96	77.47 95	84.60 136	85.07 134

EG-PatchMatch MVS		58.73 173	58.03 180	59.55 158	72.32 133	80.49 124	63.44 168	55.55 155	32.49 206	38.31 162	28.87 202	37.22 180	42.84 190	74.30 126	75.70 113	84.84 128	77.14 176

TransMVSNet (Re)		57.83 176	56.90 183	58.91 164	72.26 134	74.69 174	63.57 167	61.42 101	32.30 207	32.65 186	33.97 189	35.96 189	39.17 196	73.84 131	72.84 152	84.37 141	74.69 182

CMPMVS	43.63 17	57.67 179	55.43 187	60.28 154	72.01 135	79.00 137	62.77 172	53.23 175	41.77 176	45.42 121	30.74 198	39.03 172	53.01 159	64.81 190	64.65 196	75.26 205	68.03 203
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
NR-MVSNet		61.08 159	62.09 156	59.90 155	71.96 136	75.87 163	63.60 166	61.96 92	49.31 146	27.95 195	42.76 136	33.85 199	48.82 171	74.35 124	74.05 134	85.13 118	84.45 139

tttt0517		67.99 105	70.61 97	64.94 118	71.94 137	83.96 96	67.62 142	57.98 126	59.30 103	49.90 108	54.50 90	57.98 106	57.92 141	76.48 100	77.47 95	84.24 143	84.58 138

PMMVS		70.37 89	75.06 69	64.90 119	71.46 138	81.88 107	64.10 159	55.64 153	71.31 62	46.69 117	70.69 39	58.56 96	69.53 70	79.03 74	75.63 114	81.96 174	88.32 108

test-LLR		68.23 103	71.61 90	64.28 126	71.37 139	81.32 116	63.98 162	61.03 103	58.62 105	42.96 138	52.74 95	61.65 80	57.74 144	75.64 110	78.09 90	88.61 25	93.21 47

test0.0.03 1		57.35 180	59.89 172	54.38 187	71.37 139	73.45 179	52.71 196	61.03 103	46.11 161	26.33 199	41.73 147	44.08 153	29.72 202	71.43 157	70.90 169	85.10 119	71.56 195

tfpnnormal		58.97 170	56.48 185	61.89 145	71.27 141	76.21 162	66.65 151	61.76 98	32.90 205	36.41 172	27.83 204	29.14 212	50.64 168	73.06 138	73.05 149	84.58 138	83.15 153

Fast-Effi-MVS+-dtu		63.05 141	64.72 137	61.11 149	71.21 142	76.81 158	70.72 123	43.13 207	52.51 138	35.34 178	46.55 129	46.36 148	61.40 116	71.57 156	71.44 163	84.84 128	87.79 112

MDTV_nov1_ep13		65.21 125	67.28 120	62.79 137	70.91 143	81.72 108	69.28 133	49.50 185	58.08 108	43.94 132	50.50 104	56.02 114	58.86 134	70.72 161	73.37 141	84.24 143	80.52 166

FMVSNet3		70.41 88	71.89 87	68.68 93	70.89 144	79.42 134	75.63 75	60.97 105	65.32 81	51.06 99	47.37 118	62.05 76	64.90 94	82.49 36	82.27 36	88.64 24	84.34 141

Vis-MVSNet		65.53 123	69.83 102	60.52 152	70.80 145	84.59 88	66.37 154	55.47 157	48.40 151	40.62 152	57.67 75	58.43 100	45.37 185	77.49 89	76.24 108	84.47 139	85.99 127
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CDS-MVSNet		64.22 132	65.89 132	62.28 144	70.05 146	80.59 123	69.91 128	57.98 126	43.53 170	46.58 118	48.22 112	50.76 137	46.45 179	75.68 109	76.08 109	82.70 164	86.34 122
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
UGNet		67.57 110	71.69 89	62.76 139	69.88 147	82.58 104	66.43 152	58.64 121	54.71 132	51.87 96	61.74 62	62.01 79	45.46 184	74.78 118	74.99 120	84.24 143	91.02 73
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
GA-MVS		64.55 130	65.76 133	63.12 134	69.68 148	81.56 112	69.59 130	58.16 124	45.23 165	35.58 177	47.01 125	41.82 158	59.41 129	79.62 70	78.54 82	86.32 86	86.56 119

GBi-Net		69.21 93	70.40 98	67.81 101	69.49 149	78.65 140	74.54 86	60.97 105	65.32 81	51.06 99	47.37 118	62.05 76	63.43 102	77.49 89	78.22 87	87.37 57	83.73 144

test1		69.21 93	70.40 98	67.81 101	69.49 149	78.65 140	74.54 86	60.97 105	65.32 81	51.06 99	47.37 118	62.05 76	63.43 102	77.49 89	78.22 87	87.37 57	83.73 144

FMVSNet2		68.06 104	68.57 109	67.45 106	69.49 149	78.65 140	74.54 86	60.23 117	56.29 118	49.64 109	42.13 145	57.08 109	63.43 102	81.15 55	80.99 57	87.37 57	83.73 144

UniMVSNet_NR-MVSNet		62.30 147	63.51 142	60.89 150	69.48 152	77.83 148	64.07 160	63.94 71	50.03 143	31.17 190	44.82 132	41.12 162	51.37 164	71.02 158	74.81 123	85.30 115	84.95 135

gm-plane-assit		54.99 185	57.99 181	51.49 193	69.27 153	54.42 218	32.32 221	42.59 208	21.18 221	13.71 218	23.61 210	43.84 155	60.21 124	87.09 5	86.55 5	90.81 4	89.28 96

PatchMatch-RL		62.22 151	60.69 165	64.01 127	68.74 154	75.75 166	59.27 183	60.35 114	56.09 120	53.80 92	47.06 124	36.45 184	64.80 95	68.22 178	67.22 185	77.10 200	74.02 184

CR-MVSNet		62.31 146	64.75 135	59.47 159	68.63 155	71.29 189	67.53 143	43.18 205	55.83 121	41.40 145	41.04 151	55.85 115	57.29 147	72.76 143	73.27 145	78.77 195	83.23 151

TranMVSNet+NR-MVSNet		60.38 163	61.30 161	59.30 161	68.34 156	75.57 169	63.38 169	63.78 72	46.74 157	27.73 196	42.56 140	36.84 182	47.66 174	70.36 167	74.59 126	84.91 125	82.46 156

v8		63.44 139	62.58 151	64.43 123	68.28 157	78.07 145	71.82 106	54.85 164	46.70 158	45.20 124	39.40 161	40.91 164	60.54 121	72.85 142	74.39 130	85.92 96	85.76 130

v2v482		63.68 137	62.85 149	64.65 121	68.01 158	80.46 125	71.90 105	57.60 133	44.26 167	42.82 140	39.80 160	38.62 175	61.56 114	73.06 138	74.86 122	86.03 95	88.90 102

pm-mvs1		59.21 169	59.58 174	58.77 165	67.97 159	77.07 157	64.12 158	57.20 138	34.73 202	36.86 168	35.34 184	40.54 169	43.34 189	74.32 125	73.30 144	83.13 161	81.77 162

v10		63.00 142	62.22 154	63.90 130	67.88 160	77.78 149	71.59 111	54.34 168	45.37 164	42.76 141	38.53 163	38.93 173	61.05 118	74.39 123	74.52 128	85.75 100	86.04 125

v1144		63.00 142	62.39 153	63.70 131	67.72 161	80.27 126	71.23 115	56.40 144	42.51 172	40.81 150	38.12 168	37.73 176	60.42 123	74.46 121	74.55 127	85.64 111	89.12 98

UniMVSNet (Re)		60.62 161	62.93 148	57.92 168	67.64 162	77.90 147	61.75 175	61.24 102	49.83 145	29.80 194	42.57 139	40.62 168	43.36 188	70.49 166	73.27 145	83.76 149	85.81 129

RPMNet		58.63 174	62.80 150	53.76 189	67.59 163	71.29 189	54.60 193	38.13 217	55.83 121	35.70 176	41.58 148	53.04 132	47.89 173	66.10 183	67.38 183	78.65 197	84.40 140

v148		62.00 153	61.19 162	62.96 135	67.46 164	79.49 133	67.87 139	57.66 132	42.30 173	45.02 126	38.20 167	38.89 174	54.77 155	69.83 172	72.60 154	84.96 122	87.01 116

IterMVS		61.87 154	63.55 141	59.90 155	67.29 165	72.20 183	67.34 146	48.56 188	47.48 154	37.86 166	47.07 123	48.27 141	54.08 157	72.12 149	73.71 136	84.30 142	83.99 143
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1192		62.25 148	61.64 158	62.96 135	66.88 166	79.72 130	69.96 127	55.77 151	41.58 177	39.42 155	37.05 173	35.96 189	60.50 122	74.30 126	74.09 132	85.24 117	88.76 103

DU-MVS		60.87 160	61.82 157	59.76 157	66.69 167	75.87 163	64.07 160	61.96 92	49.31 146	31.17 190	42.76 136	36.95 181	51.37 164	69.67 173	73.20 148	83.30 156	84.95 135

Baseline_NR-MVSNet		59.47 167	60.28 168	58.54 166	66.69 167	73.90 177	61.63 176	62.90 84	49.15 150	26.87 197	35.18 186	37.62 177	48.20 172	69.67 173	73.61 137	84.92 123	82.82 154

IterMVS-SCA-FT		60.21 164	62.97 146	57.00 176	66.64 169	71.84 184	67.53 143	46.93 195	47.56 153	36.77 171	46.85 127	48.21 142	52.51 160	70.36 167	72.40 156	71.63 213	83.53 147

v144192		62.05 152	61.46 160	62.73 141	66.59 170	79.87 129	69.30 132	55.88 149	41.50 179	39.41 156	37.23 171	36.45 184	59.62 127	72.69 145	73.51 138	85.61 112	88.93 100

v1921920		61.66 155	61.10 163	62.31 143	66.32 171	79.57 132	68.41 137	55.49 156	41.03 180	38.69 160	36.64 179	35.27 192	59.60 128	73.23 136	73.41 140	85.37 114	88.51 107

TESTMET0.1,1		67.38 112	71.61 90	62.45 142	66.05 172	81.32 116	63.98 162	55.36 158	58.62 105	42.96 138	52.74 95	61.65 80	57.74 144	75.64 110	78.09 90	88.61 25	93.21 47

pmmvs4		63.14 140	62.46 152	63.94 129	66.03 173	76.40 160	66.82 149	57.60 133	56.74 114	50.26 106	40.81 154	37.51 178	59.26 131	71.75 154	71.48 162	83.68 152	82.53 155

PatchT		60.46 162	63.85 140	56.51 178	65.95 174	75.68 167	47.34 204	41.39 212	53.89 135	41.40 145	37.84 169	50.30 139	57.29 147	72.76 143	73.27 145	85.67 107	83.23 151

v1240		61.09 158	60.55 167	61.72 147	65.92 175	79.28 135	67.16 147	54.91 163	39.79 186	38.10 163	36.08 181	34.64 194	59.15 132	72.86 141	73.36 142	85.10 119	87.84 111

ADS-MVSNet		58.40 175	59.16 176	57.52 172	65.80 176	74.57 175	60.26 179	40.17 216	50.51 141	38.01 164	40.11 159	44.72 152	59.36 130	64.91 188	66.55 188	81.53 178	72.72 192

FMVSNet1		63.48 138	63.07 145	63.97 128	65.31 177	76.37 161	71.77 109	57.90 129	43.32 171	45.66 120	35.06 187	49.43 140	58.57 135	77.49 89	78.22 87	84.59 137	81.60 163

testgi		48.51 205	50.53 203	46.16 205	64.78 178	67.15 200	41.54 214	54.81 165	29.12 212	17.03 210	32.07 194	31.98 202	20.15 216	65.26 187	67.00 187	78.67 196	61.10 216

LTVRE_ROB	47.26 16	49.41 203	49.91 206	48.82 197	64.76 179	69.79 192	49.05 200	47.12 194	20.36 223	16.52 212	36.65 178	26.96 215	50.76 167	60.47 199	63.16 201	64.73 216	72.00 193
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
Anonymous20231206		52.23 195	52.80 197	51.56 192	64.70 180	69.41 193	51.01 198	58.60 122	36.63 194	22.44 205	21.80 215	31.42 206	30.52 201	66.79 182	67.83 182	82.10 173	75.73 178

thisisatest0515		59.37 168	60.68 166	57.84 170	64.39 181	75.65 168	58.56 186	53.86 171	41.55 178	42.12 143	40.40 156	39.59 171	47.09 177	71.69 155	73.79 135	81.02 182	82.08 160

USDC		59.69 166	60.03 171	59.28 162	64.04 182	71.84 184	63.15 171	55.36 158	54.90 130	35.02 179	48.34 111	29.79 211	58.16 136	70.60 163	71.33 167	79.99 188	73.42 188

WR-MVS		51.02 197	54.56 189	46.90 203	63.84 183	69.23 194	44.78 211	56.38 145	38.19 190	14.19 216	37.38 170	36.82 183	22.39 212	60.14 200	66.20 192	79.81 189	73.95 186

our_test_3					63.32 184	71.07 191	55.90 191

test20.03		47.23 208	48.69 208	45.53 207	63.28 185	64.39 206	41.01 215	56.93 142	29.16 211	15.21 215	23.90 209	30.76 209	17.51 219	64.63 191	65.26 193	79.21 194	62.71 213

UniMVSNet_ETH3D		57.83 176	56.46 186	59.43 160	63.24 186	73.22 180	67.70 140	55.58 154	36.17 197	36.84 169	32.64 191	35.14 193	51.50 163	65.81 184	69.81 177	81.73 176	82.44 158

pmmvs6		54.20 190	53.54 192	54.97 182	63.22 187	72.98 181	60.17 180	52.32 180	26.77 216	34.30 182	23.29 212	36.23 186	40.33 195	68.77 177	68.76 180	79.47 193	78.00 174

v7n		57.04 181	56.64 184	57.52 172	62.85 188	74.75 173	61.76 174	51.80 181	35.58 201	36.02 175	32.33 193	33.61 200	50.16 169	67.73 180	70.34 175	82.51 166	82.12 159

pmmvs5		59.72 165	60.24 169	59.11 163	62.77 189	77.33 155	63.17 170	54.00 170	40.21 184	37.23 167	40.41 155	35.99 188	51.75 162	72.55 147	72.74 153	85.72 105	82.45 157

CVMVSNet		54.92 187	58.16 178	51.13 194	62.61 190	68.44 196	55.45 192	52.38 179	42.28 174	21.45 206	47.10 122	46.10 149	37.96 197	64.42 193	63.81 197	76.92 201	75.01 181

TAMVS		58.86 171	60.91 164	56.47 179	62.38 191	77.57 151	58.97 185	52.98 176	38.76 189	36.17 173	42.26 144	47.94 144	46.45 179	70.23 169	70.79 171	81.86 175	78.82 172

pmnet_mix02		53.92 191	53.30 193	54.65 186	61.89 192	71.33 188	54.54 194	54.17 169	40.38 182	34.65 180	34.76 188	30.68 210	40.44 194	60.97 198	63.71 198	82.19 172	71.24 197

DTE-MVSNet		49.82 201	51.92 201	47.37 202	61.75 193	64.38 207	45.89 210	57.33 137	36.11 198	12.79 221	36.87 175	31.93 204	25.73 209	58.01 202	65.22 194	80.75 185	70.93 199

PEN-MVS		51.04 196	52.94 195	48.82 197	61.45 194	66.00 202	48.68 201	57.20 138	36.87 192	15.36 214	36.98 174	32.72 201	28.77 206	57.63 204	66.37 189	81.44 179	74.00 185

V42		62.86 144	62.97 146	62.74 140	60.84 195	78.99 138	71.46 113	57.13 140	46.85 156	44.28 130	38.87 162	40.73 167	57.63 146	72.60 146	74.14 131	85.09 121	88.63 104

MDTV_nov1_ep13_2view		54.47 189	54.61 188	54.30 188	60.50 196	73.82 178	57.92 187	43.38 204	39.43 188	32.51 187	33.23 190	34.05 197	47.26 176	62.36 196	66.21 191	84.24 143	73.19 190

MVS-HIRNet		53.86 192	53.02 194	54.85 183	60.30 197	72.36 182	44.63 212	42.20 210	39.45 187	43.47 134	21.66 216	34.00 198	55.47 152	65.42 186	67.16 186	83.02 162	71.08 198

CHOSEN 280x420		62.23 150	66.57 125	57.17 175	59.88 198	68.92 195	61.20 178	42.28 209	54.17 133	39.57 153	47.78 115	64.97 66	62.68 107	73.85 130	69.52 179	77.43 199	86.75 117

TinyColmap		52.66 194	50.09 205	55.65 180	59.72 199	64.02 209	57.15 189	52.96 177	40.28 183	32.51 187	32.42 192	20.97 222	56.65 149	63.95 194	65.15 195	74.91 206	63.87 210

FC-MVSNet-test		47.24 207	54.37 190	38.93 212	59.49 200	58.25 216	34.48 220	53.36 174	45.66 163	6.66 226	50.62 102	42.02 157	16.62 220	58.39 201	61.21 205	62.99 217	64.40 209

test-mter		64.06 134	69.24 104	58.01 167	59.07 201	77.40 153	59.13 184	48.11 190	55.64 124	39.18 158	51.56 100	58.54 97	55.38 153	73.52 134	76.00 110	87.22 67	92.05 63

WR-MVS_H		49.62 202	52.63 198	46.11 206	58.80 202	67.58 198	46.14 209	54.94 161	36.51 195	13.63 219	36.75 177	35.67 191	22.10 213	56.43 208	62.76 202	81.06 181	72.73 191

CP-MVSNet		50.57 198	52.60 199	48.21 200	58.77 203	65.82 203	48.17 202	56.29 146	37.41 191	16.59 211	37.14 172	31.95 203	29.21 203	56.60 207	63.71 198	80.22 186	75.56 179

PS-CasMVS		50.17 199	52.02 200	48.02 201	58.60 204	65.54 204	48.04 203	56.19 148	36.42 196	16.42 213	35.68 183	31.33 207	28.85 205	56.42 209	63.54 200	80.01 187	75.18 180

SixPastTwentyTwo		49.11 204	49.22 207	48.99 196	58.54 205	64.14 208	47.18 205	47.75 191	31.15 209	24.42 201	41.01 152	26.55 216	44.04 187	54.76 212	58.70 209	71.99 212	68.21 201

TDRefinement		52.70 193	51.02 202	54.66 185	57.41 206	65.06 205	61.47 177	54.94 161	44.03 168	33.93 183	30.13 200	27.57 214	46.17 181	61.86 197	62.48 204	74.01 209	66.06 206

pmmvs-eth3d		55.20 182	53.95 191	56.65 177	57.34 207	67.77 197	57.54 188	53.74 172	40.93 181	41.09 149	31.19 197	29.10 213	49.07 170	65.54 185	67.28 184	81.14 180	75.81 177

FPMVS		39.11 214	36.39 216	42.28 208	55.97 208	45.94 221	46.23 208	41.57 211	35.73 200	22.61 203	23.46 211	19.82 224	28.32 207	43.57 217	40.67 219	58.96 219	45.54 219

MIMVSNet		57.78 178	59.71 173	55.53 181	54.79 209	77.10 156	63.89 164	45.02 199	46.59 159	36.79 170	28.36 203	40.77 166	45.84 183	74.97 115	76.58 102	86.87 75	73.60 187

N_pmnet		47.67 206	47.00 210	48.45 199	54.72 210	62.78 210	46.95 206	51.25 182	36.01 199	26.09 200	26.59 207	25.93 219	35.50 199	55.67 211	59.01 207	76.22 202	63.04 211

anonymousdsp		54.99 185	57.24 182	52.36 190	53.82 211	71.75 187	51.49 197	48.14 189	33.74 203	33.66 184	38.34 165	36.13 187	47.54 175	64.53 192	70.60 173	79.53 192	85.59 132

new-patchmatchnet		42.21 211	42.97 212	41.33 210	53.05 212	59.89 213	39.38 216	49.61 184	28.26 214	12.10 222	22.17 214	21.54 221	19.22 217	50.96 214	56.04 212	74.61 208	61.92 214

FMVSNet5		58.86 171	60.24 169	57.25 174	52.66 213	66.25 201	63.77 165	52.86 178	57.85 112	37.92 165	36.12 180	52.22 134	51.37 164	70.88 160	71.43 164	84.92 123	66.91 205

ET-MVSNet_ETH3D		71.38 83	74.70 72	67.51 104	51.61 214	88.06 51	77.29 68	60.95 108	63.61 87	48.36 113	66.60 50	60.67 87	79.55 10	73.56 133	80.58 65	87.30 63	89.80 90

WB-MVS		30.42 217	32.63 219	27.84 216	51.51 215	41.64 223	17.75 226	55.06 160	20.11 224	2.46 231	26.13 208	16.63 227	3.90 226	44.91 215	44.54 218	36.34 225	34.48 222

ambc			42.30 213		50.36 216	49.51 220	35.47 219		32.04 208	23.53 202	17.36 219	8.95 230	29.06 204	64.88 189	56.26 211	61.29 218	67.12 204

EU-MVSNet		44.84 209	47.85 209	41.32 211	49.26 217	56.59 217	43.07 213	47.64 193	33.03 204	13.82 217	36.78 176	30.99 208	24.37 210	53.80 213	55.57 213	69.78 214	68.21 201

RPSCF		55.07 184	58.06 179	51.57 191	48.87 218	58.95 214	53.68 195	41.26 214	62.42 91	45.88 119	54.38 91	54.26 126	53.75 158	57.15 205	53.53 215	66.01 215	65.75 207

PMVS	27.44 18	32.08 216	29.07 220	35.60 214	48.33 219	24.79 225	26.97 223	41.34 213	20.45 222	22.50 204	17.11 221	18.64 225	20.44 215	41.99 219	38.06 220	54.02 221	42.44 220
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PM-MVS		50.11 200	50.38 204	49.80 195	47.23 220	62.08 212	50.91 199	44.84 201	41.90 175	36.10 174	35.22 185	26.05 218	46.83 178	57.64 203	55.42 214	72.90 210	74.32 183

pmmvs3		41.86 212	42.29 214	41.36 209	39.80 221	52.66 219	38.93 218	35.85 221	23.40 220	20.22 208	19.30 217	20.84 223	40.56 193	55.98 210	58.79 208	72.80 211	65.03 208

MDA-MVSNet-bldmvs		44.15 210	42.27 215	46.34 204	38.34 222	62.31 211	46.28 207	55.74 152	29.83 210	20.98 207	27.11 206	16.45 228	41.98 191	41.11 220	57.47 210	74.72 207	61.65 215

MIMVSNet1		40.84 213	43.46 211	37.79 213	32.14 223	58.92 215	39.24 217	50.83 183	27.00 215	11.29 223	16.76 222	26.53 217	17.75 218	57.14 206	61.12 206	75.46 204	56.78 217

Gipuma		24.91 219	24.61 221	25.26 218	31.47 224	21.59 226	18.06 225	37.53 218	25.43 218	10.03 224	4.18 228	4.25 232	14.85 221	43.20 218	47.03 216	39.62 223	26.55 225
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		15.08 221	11.65 224	19.08 220	28.73 225	12.31 230	6.95 231	36.87 220	10.71 227	3.63 229	5.13 225	2.22 235	13.81 223	11.34 226	18.50 225	24.49 227	21.32 226

EMVS		14.40 222	10.71 225	18.70 221	28.15 226	12.09 231	7.06 230	36.89 219	11.00 226	3.56 230	4.95 226	2.27 234	13.91 222	10.13 227	16.06 226	22.63 228	18.51 227

new_pmnet		33.19 215	35.52 217	30.47 215	27.55 227	45.31 222	29.29 222	30.92 222	29.00 213	9.88 225	18.77 218	17.64 226	26.77 208	44.07 216	45.98 217	58.41 220	47.87 218

PMMVS2		20.45 220	22.31 222	18.27 222	20.52 228	26.73 224	14.85 228	28.43 224	13.69 225	0.79 232	10.35 224	9.10 229	3.83 227	27.64 223	32.87 221	41.17 222	35.81 221

tmp_tt				16.09 223	13.07 229	8.12 232	13.61 229	2.08 227	55.09 127	30.10 193	40.26 157	22.83 220	5.35 225	29.91 222	25.25 224	32.33 226

MVE	15.98 19	14.37 223	16.36 223	12.04 224	7.72 230	20.24 228	5.90 232	29.05 223	8.28 228	3.92 228	4.72 227	2.42 233	9.57 224	18.89 225	31.46 222	16.07 230	28.53 224
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		28.15 218	34.48 218	20.76 219	6.76 231	21.18 227	21.03 224	18.41 225	36.77 193	17.52 209	15.67 223	31.63 205	24.05 211	41.03 221	26.69 223	36.82 224	68.38 200

GG-mvs-BLEND		54.54 188	77.58 52	27.67 217	0.03 232	90.09 29	77.20 70	0.02 228	66.83 75	0.05 233	59.90 70	73.33 36	0.04 228	78.40 81	79.30 77	88.65 23	95.20 26

uanet_test		0.00 226	0.00 228	0.00 227	0.00 233	0.00 235	0.00 236	0.00 230	0.00 231	0.00 234	0.00 231	0.00 237	0.00 231	0.00 230	0.00 229	0.00 232	0.00 230

sosnet-low-res		0.00 226	0.00 228	0.00 227	0.00 233	0.00 235	0.00 236	0.00 230	0.00 231	0.00 234	0.00 231	0.00 237	0.00 231	0.00 230	0.00 229	0.00 232	0.00 230

sosnet		0.00 226	0.00 228	0.00 227	0.00 233	0.00 235	0.00 236	0.00 230	0.00 231	0.00 234	0.00 231	0.00 237	0.00 231	0.00 230	0.00 229	0.00 232	0.00 230

testmvs		0.05 224	0.08 226	0.01 225	0.00 233	0.01 233	0.03 234	0.01 229	0.05 229	0.00 234	0.14 230	0.01 236	0.03 230	0.05 228	0.05 227	0.01 231	0.24 229

test123		0.05 224	0.08 226	0.01 225	0.00 233	0.01 233	0.01 235	0.00 230	0.05 229	0.00 234	0.16 229	0.00 237	0.04 228	0.02 229	0.05 227	0.00 232	0.26 228

RE-MVS-def										31.47 189

9.14												84.47 7

MTAPA										78.32 11		79.42 26

MTMP										76.04 15		76.65 30

Patchmatch-RL test							2.17 233

NP-MVS									81.60 35

Patchmtry						78.06 146	67.53 143	43.18 205		41.40 145

DeepMVS_CX						19.81 229	17.01 227	10.02 226	23.61 219	5.85 227	17.21 220	8.03 231	21.13 214	22.60 224		21.42 229	30.01 223

High-resolution multi-view benchmark