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		77.13 8	81.70 8	71.79 3	79.32 1	80.76 5	82.96 2	57.49 11	82.82 9	64.79 5	83.69 10	84.46 5	62.83 13	77.13 26	75.21 32	83.35 7	87.85 16

SED-MVS		79.21 1	84.74 2	72.75 1	78.66 2	81.96 2	82.94 4	58.16 4	86.82 2	67.66 1	88.29 4	86.15 3	66.42 2	80.41 4	78.65 6	82.65 16	90.92 2

DVP-MVS		78.77 2	84.89 1	71.62 4	78.04 3	82.05 1	81.64 10	57.96 7	87.53 1	66.64 2	88.77 1	86.31 1	63.16 10	79.99 7	78.56 7	82.31 23	91.03 1
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
APDe-MVS		77.58 6	82.93 6	71.35 6	77.86 4	80.55 6	83.38 1	57.61 10	85.57 5	61.11 22	86.10 7	82.98 8	64.76 4	78.29 15	76.78 22	83.40 6	90.20 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPE-MVS		78.11 4	83.84 4	71.42 5	77.82 5	81.32 4	82.92 5	57.81 9	84.04 8	63.19 12	88.63 2	86.00 4	64.52 5	78.71 11	77.63 15	82.26 24	90.57 3
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SteuartSystems-ACMMP		75.23 13	79.60 15	70.13 13	76.81 6	78.92 12	81.74 8	57.99 6	75.30 29	59.83 27	75.69 18	78.45 24	60.48 29	80.58 2	79.77 2	83.94 3	88.52 10
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS++		78.76 3	84.44 3	72.14 2	76.63 7	81.93 3	82.92 5	58.10 5	85.86 4	66.53 3	87.86 5	86.16 2	66.45 1	80.46 3	78.53 9	82.19 28	90.29 4

HPM-MVS++		76.01 10	80.47 12	70.81 9	76.60 8	74.96 36	80.18 17	58.36 2	81.96 10	63.50 11	78.80 14	82.53 11	64.40 6	78.74 10	78.84 5	81.81 34	87.46 18

MCST-MVS		73.67 24	77.39 26	69.33 18	76.26 9	78.19 17	78.77 26	54.54 30	75.33 27	59.99 26	67.96 32	79.23 22	62.43 16	78.00 18	75.71 30	84.02 2	87.30 19

CNVR-MVS		75.62 12	79.91 14	70.61 10	75.76 10	78.82 14	81.66 9	57.12 13	79.77 16	63.04 13	70.69 25	81.15 16	62.99 11	80.23 5	79.54 3	83.11 8	89.16 8

NCCC		74.27 19	77.83 24	70.13 13	75.70 11	77.41 23	80.51 15	57.09 14	78.25 20	62.28 18	65.54 37	78.26 25	62.18 18	79.13 8	78.51 10	83.01 10	87.68 17

CSCG		74.68 16	79.22 16	69.40 17	75.69 12	80.01 9	79.12 24	52.83 41	79.34 17	63.99 9	70.49 26	82.02 12	60.35 32	77.48 24	77.22 19	84.38 1	87.97 15

DPM-MVS		72.80 26	75.90 30	69.19 20	75.51 13	77.68 21	81.62 11	54.83 26	75.96 25	62.06 19	63.96 49	76.58 31	58.55 40	76.66 33	76.77 23	82.60 19	83.68 40

TPM-MVS					75.48 14	76.70 30	79.31 21			62.34 17	64.71 42	77.88 28	56.94 53			81.88 32	83.68 40
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
SMA-MVS		77.32 7	82.51 7	71.26 7	75.43 15	80.19 8	82.22 7	58.26 3	84.83 7	64.36 7	78.19 15	83.46 6	63.61 8	81.00 1	80.28 1	83.66 4	89.62 6
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
APD-MVS		75.80 11	80.90 11	69.86 15	75.42 16	78.48 16	81.43 13	57.44 12	80.45 14	59.32 28	85.28 8	80.82 18	63.96 7	76.89 28	76.08 28	81.58 39	88.30 12
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MSP-MVS		77.82 5	83.46 5	71.24 8	75.26 17	80.22 7	82.95 3	57.85 8	85.90 3	64.79 5	88.54 3	83.43 7	66.24 3	78.21 17	78.56 7	80.34 46	89.39 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
train_agg		73.89 21	78.25 22	68.80 23	75.25 18	72.27 51	79.75 18	56.05 20	74.87 32	58.97 29	81.83 11	79.76 21	61.05 25	77.39 25	76.01 29	81.71 37	85.61 30

TSAR-MVS + MP.		75.22 14	80.06 13	69.56 16	74.61 19	72.74 49	80.59 14	55.70 23	80.80 13	62.65 15	86.25 6	82.92 9	62.07 19	76.89 28	75.66 31	81.77 36	85.19 33
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		74.43 17	78.87 18	69.26 19	74.39 20	73.70 45	79.06 25	55.24 25	81.04 12	62.71 14	80.18 12	82.61 10	61.70 21	75.43 40	73.92 43	82.44 22	85.22 32
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
ACMMP_NAP		76.15 9	81.17 9	70.30 11	74.09 21	79.47 10	81.59 12	57.09 14	81.38 11	63.89 10	79.02 13	80.48 19	62.24 17	80.05 6	79.12 4	82.94 11	88.64 9

HFP-MVS		74.87 15	78.86 20	70.21 12	73.99 22	77.91 18	80.36 16	56.63 16	78.41 19	64.27 8	74.54 20	77.75 29	62.96 12	78.70 12	77.82 13	83.02 9	86.91 21

AdaColmap		67.89 45	68.85 60	66.77 29	73.73 23	74.30 43	75.28 41	53.58 36	70.24 47	57.59 36	51.19 107	59.19 96	60.74 28	75.33 42	73.72 45	79.69 54	77.96 72

MP-MVS		74.31 18	78.87 18	68.99 21	73.49 24	78.56 15	79.25 23	56.51 17	75.33 27	60.69 24	75.30 19	79.12 23	61.81 20	77.78 21	77.93 12	82.18 30	88.06 14
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + ACMM		72.56 28	79.07 17	64.96 41	73.24 25	73.16 48	78.50 27	48.80 67	79.34 17	55.32 42	85.04 9	81.49 15	58.57 39	75.06 43	73.75 44	75.35 109	85.61 30

CDPH-MVS		71.47 32	75.82 32	66.41 32	72.97 26	77.15 25	78.14 30	54.71 27	69.88 49	53.07 56	70.98 24	74.83 37	56.95 52	76.22 34	76.57 24	82.62 17	85.09 34

PGM-MVS		72.89 25	77.13 27	67.94 25	72.47 27	77.25 24	79.27 22	54.63 29	73.71 36	57.95 35	72.38 23	75.33 35	60.75 27	78.25 16	77.36 18	82.57 20	85.62 29

ACMMPR		73.79 23	78.41 21	68.40 24	72.35 28	77.79 20	79.32 20	56.38 18	77.67 23	58.30 33	74.16 21	76.66 30	61.40 22	78.32 14	77.80 14	82.68 15	86.51 22

OPM-MVS		69.33 37	71.05 46	67.32 27	72.34 29	75.70 33	79.57 19	56.34 19	55.21 77	53.81 53	59.51 68	68.96 58	59.67 34	77.61 23	76.44 26	82.19 28	83.88 39
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
X-MVS		71.18 33	75.66 33	65.96 36	71.71 30	76.96 26	77.26 33	55.88 22	72.75 40	54.48 49	64.39 44	74.47 38	54.19 67	77.84 20	77.37 17	82.21 27	85.85 27

HQP-MVS		70.88 34	75.02 34	66.05 35	71.69 31	74.47 41	77.51 32	53.17 38	72.89 39	54.88 46	70.03 28	70.48 52	57.26 48	76.02 36	75.01 35	81.78 35	86.21 23

MAR-MVS		68.04 44	70.74 48	64.90 42	71.68 32	76.33 32	74.63 44	50.48 55	63.81 57	55.52 41	54.88 87	69.90 54	57.39 47	75.42 41	74.79 37	79.71 51	80.03 57
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
mPP-MVS					71.67 33							74.36 41

SR-MVS					71.46 34			54.67 28				81.54 14

MVS_0304		72.45 29	77.44 25	66.61 30	71.08 35	77.81 19	76.74 34	49.30 61	73.12 38	61.17 20	73.70 22	78.08 26	58.78 37	76.75 32	76.52 25	82.61 18	86.14 25

CLD-MVS		67.02 49	71.57 43	61.71 51	71.01 36	74.81 38	71.62 51	38.91 164	71.86 43	60.70 23	64.97 41	67.88 66	51.88 93	76.77 31	74.98 36	76.11 97	69.75 127
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CP-MVS		72.63 27	76.95 28	67.59 26	70.67 37	75.53 34	77.95 31	56.01 21	75.65 26	58.82 30	69.16 30	76.48 32	60.46 30	77.66 22	77.20 20	81.65 38	86.97 20

ACMM	60.30 7	67.58 47	68.82 61	66.13 34	70.59 38	72.01 53	76.54 36	54.26 32	65.64 55	54.78 48	50.35 110	61.72 85	58.74 38	75.79 38	75.03 34	81.88 32	81.17 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVS					70.49 39	76.96 26	74.36 45			54.48 49		74.47 38				82.24 25

X-MVStestdata					70.49 39	76.96 26	74.36 45			54.48 49		74.47 38				82.24 25

ACMMP		71.57 31	75.84 31	66.59 31	70.30 41	76.85 29	78.46 28	53.95 34	73.52 37	55.56 40	70.13 27	71.36 50	58.55 40	77.00 27	76.23 27	82.71 14	85.81 28
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
MVS_111021_HR		67.62 46	70.39 50	64.39 44	69.77 42	70.45 59	71.44 53	51.72 47	60.77 65	55.06 44	62.14 59	66.40 70	58.13 43	76.13 35	74.79 37	80.19 48	82.04 49

MSLP-MVS++		68.17 43	70.72 49	65.19 39	69.41 43	70.64 56	74.99 42	45.76 77	70.20 48	60.17 25	56.42 79	73.01 44	61.14 23	72.80 54	70.54 59	79.70 52	81.42 51

LGP-MVS_train		68.87 39	72.03 42	65.18 40	69.33 44	74.03 44	76.67 35	53.88 35	68.46 50	52.05 61	63.21 51	63.89 74	56.31 56	75.99 37	74.43 39	82.83 13	84.18 36

ACMP	61.42 5	68.72 42	71.37 44	65.64 38	69.06 45	74.45 42	75.88 39	53.30 37	68.10 51	55.74 39	61.53 62	62.29 81	56.97 51	74.70 46	74.23 41	82.88 12	84.31 35
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DeepC-MVS_fast	65.08 3	72.00 30	76.11 29	67.21 28	68.93 46	77.46 22	76.54 36	54.35 31	74.92 31	58.64 32	65.18 39	74.04 43	62.62 14	77.92 19	77.02 21	82.16 31	86.21 23
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CANet		68.77 40	73.01 37	63.83 45	68.30 47	75.19 35	73.73 48	47.90 68	63.86 56	54.84 47	67.51 34	74.36 41	57.62 44	74.22 48	73.57 47	80.56 44	82.36 46

TSAR-MVS + GP.		69.71 35	73.92 36	64.80 43	68.27 48	70.56 57	71.90 50	50.75 51	71.38 44	57.46 37	68.68 31	75.42 34	60.10 33	73.47 51	73.99 42	80.32 47	83.97 38

3Dnovator+	62.63 4	69.51 36	72.62 39	65.88 37	68.21 49	76.47 31	73.50 49	52.74 42	70.85 45	58.65 31	55.97 81	69.95 53	61.11 24	76.80 30	75.09 33	81.09 42	83.23 44

DeepC-MVS	66.32 2	73.85 22	78.10 23	68.90 22	67.92 50	79.31 11	78.16 29	59.28 1	78.24 21	61.13 21	67.36 35	76.10 33	63.40 9	79.11 9	78.41 11	83.52 5	88.16 13
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepPCF-MVS	66.49 1	74.25 20	80.97 10	66.41 32	67.75 51	78.87 13	75.61 40	54.16 33	84.86 6	58.22 34	77.94 16	81.01 17	62.52 15	78.34 13	77.38 16	80.16 49	88.40 11

EC-MVSNet		67.01 50	70.27 53	63.21 47	67.21 52	70.47 58	69.01 57	46.96 71	59.16 69	53.23 55	64.01 48	69.71 56	60.37 31	74.92 44	71.24 55	82.50 21	82.41 45

UA-Net		58.50 94	64.68 81	51.30 123	66.97 53	67.13 86	53.68 165	45.65 80	49.51 110	31.58 151	62.91 53	68.47 60	35.85 175	68.20 102	67.28 97	74.03 121	69.24 137

PHI-MVS		69.27 38	74.84 35	62.76 50	66.83 54	74.83 37	73.88 47	49.32 60	70.61 46	50.93 64	69.62 29	74.84 36	57.25 49	75.53 39	74.32 40	78.35 68	84.17 37

3Dnovator	60.86 6	66.99 51	70.32 51	63.11 48	66.63 55	74.52 39	71.56 52	45.76 77	67.37 53	55.00 45	54.31 92	68.19 62	58.49 42	73.97 49	73.63 46	81.22 41	80.23 56

EPNet		65.14 60	69.54 57	60.00 58	66.61 56	67.67 77	67.53 65	55.32 24	62.67 61	46.22 83	67.74 33	65.93 71	48.07 113	72.17 57	72.12 49	76.28 93	78.47 68
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OpenMVS	57.13 9	62.81 67	65.75 73	59.39 62	66.47 57	69.52 61	64.26 100	43.07 130	61.34 64	50.19 67	47.29 128	64.41 73	54.60 65	70.18 79	68.62 80	77.73 70	78.89 64

ACMH	52.42 13	58.24 101	59.56 121	56.70 86	66.34 58	69.59 60	66.71 74	49.12 62	46.08 143	28.90 164	42.67 175	41.20 192	52.60 85	71.39 63	70.28 61	76.51 89	75.72 94
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MSDG		58.46 96	58.97 127	57.85 78	66.27 59	66.23 95	67.72 62	42.33 134	53.43 85	43.68 95	43.39 166	45.35 169	49.75 102	68.66 93	67.77 89	77.38 76	67.96 142

QAPM		65.27 56	69.49 58	60.35 55	65.43 60	72.20 52	65.69 87	47.23 69	63.46 58	49.14 69	53.56 93	71.04 51	57.01 50	72.60 56	71.41 53	77.62 72	82.14 48

CPTT-MVS		68.76 41	73.01 37	63.81 46	65.42 61	73.66 46	76.39 38	52.08 43	72.61 41	50.33 66	60.73 63	72.65 46	59.43 35	73.32 52	72.12 49	79.19 60	85.99 26

MS-PatchMatch		58.19 103	60.20 108	55.85 92	65.17 62	64.16 115	64.82 94	41.48 143	50.95 100	42.17 104	45.38 149	56.42 108	48.08 112	68.30 98	66.70 106	73.39 130	69.46 135

PCF-MVS	59.98 8	67.32 48	71.04 47	62.97 49	64.77 63	74.49 40	74.78 43	49.54 57	67.44 52	54.39 52	58.35 73	72.81 45	55.79 62	71.54 62	69.24 70	78.57 62	83.41 42
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EG-PatchMatch MVS		56.98 110	58.24 134	55.50 94	64.66 64	68.62 65	61.48 109	43.63 114	38.44 196	41.44 106	38.05 187	46.18 164	43.95 131	71.71 61	70.61 58	77.87 69	74.08 107

Effi-MVS+-dtu		60.34 81	62.32 91	58.03 73	64.31 65	67.44 81	65.99 81	42.26 135	49.55 108	42.00 105	48.92 118	59.79 94	56.27 57	68.07 106	67.03 98	77.35 77	75.45 97

FC-MVSNet-train		58.40 97	63.15 88	52.85 113	64.29 66	61.84 128	55.98 149	46.47 73	53.06 89	34.96 139	61.95 61	56.37 110	39.49 152	68.67 92	68.36 82	75.92 103	71.81 115

Effi-MVS+		63.28 64	65.96 72	60.17 57	64.26 67	68.06 71	68.78 60	45.71 79	54.08 81	46.64 79	55.92 82	63.13 78	55.94 60	70.38 76	71.43 52	79.68 55	78.70 65

LS3D		60.20 82	61.70 92	58.45 68	64.18 68	67.77 74	67.19 67	48.84 66	61.67 63	41.27 109	45.89 143	51.81 127	54.18 68	68.78 90	66.50 113	75.03 113	69.48 133

ACMH+	53.71 12	59.26 86	60.28 105	58.06 71	64.17 69	68.46 66	67.51 66	50.93 50	52.46 95	35.83 135	40.83 180	45.12 173	52.32 88	69.88 81	69.00 75	77.59 74	76.21 91

GeoE		62.43 70	64.79 80	59.68 61	64.15 70	67.17 85	68.80 59	44.42 96	55.65 76	47.38 73	51.54 104	62.51 79	54.04 70	69.99 80	68.07 84	79.28 58	78.57 66

DELS-MVS		65.87 53	70.30 52	60.71 54	64.05 71	72.68 50	70.90 54	45.43 81	57.49 72	49.05 71	64.43 43	68.66 59	55.11 64	74.31 47	73.02 48	79.70 52	81.51 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
sasdasda		65.62 54	72.06 40	58.11 69	63.94 72	71.05 54	64.49 97	43.18 126	74.08 33	47.35 74	64.17 46	71.97 47	51.17 96	71.87 58	70.74 56	78.51 65	80.56 54

canonicalmvs		65.62 54	72.06 40	58.11 69	63.94 72	71.05 54	64.49 97	43.18 126	74.08 33	47.35 74	64.17 46	71.97 47	51.17 96	71.87 58	70.74 56	78.51 65	80.56 54

EIA-MVS		61.53 76	63.79 86	58.89 66	63.82 74	67.61 78	65.35 90	42.15 138	49.98 105	45.66 86	57.47 77	56.62 106	56.59 55	70.91 70	69.15 71	79.78 50	74.80 101

Anonymous202405211			60.60 101		63.44 75	66.71 92	61.00 114	47.23 69	50.62 103		36.85 190	60.63 91	43.03 139	69.17 86	67.72 91	75.41 106	72.54 112

ETV-MVS		63.23 65	66.08 71	59.91 59	63.13 76	68.13 70	67.62 64	44.62 92	53.39 86	46.23 82	58.74 70	58.19 99	57.45 46	73.60 50	71.38 54	80.39 45	79.13 61

casdiffmvs_mvg		65.26 57	69.48 59	60.33 56	62.99 77	69.34 62	69.80 56	45.27 83	63.38 59	51.11 63	65.12 40	69.75 55	53.51 75	71.74 60	68.86 76	79.33 56	78.19 71
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
gg-mvs-nofinetune		49.07 171	52.56 171	45.00 171	61.99 78	59.78 147	53.55 167	41.63 141	31.62 212	12.08 208	29.56 208	53.28 121	29.57 190	66.27 137	64.49 140	71.19 159	62.92 176

SPE-MVS-test		65.18 58	68.70 62	61.07 53	61.92 79	68.06 71	67.09 71	45.18 85	58.47 71	52.02 62	65.76 36	66.44 69	59.24 36	72.71 55	70.05 64	80.98 43	79.40 60

DCV-MVSNet		59.49 84	64.00 85	54.23 99	61.81 80	64.33 113	61.42 110	43.77 108	52.85 92	38.94 123	55.62 84	62.15 83	43.24 138	69.39 84	67.66 93	76.22 95	75.97 92

casdiffmvs		64.09 61	68.13 63	59.37 63	61.81 80	68.32 68	68.48 61	44.45 95	61.95 62	49.12 70	63.04 52	69.67 57	53.83 71	70.46 73	66.06 118	78.55 63	77.43 75
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		65.88 52	69.71 56	61.41 52	61.76 82	68.14 69	67.65 63	44.00 105	59.14 70	52.69 57	65.19 38	68.13 63	60.90 26	74.74 45	71.58 51	81.46 40	81.04 53

Anonymous20231211		57.71 106	60.79 98	54.13 101	61.68 83	65.81 99	60.81 115	43.70 112	51.97 98	39.67 118	34.82 195	63.59 75	43.31 136	68.55 96	66.63 109	75.59 104	74.13 106

IS_MVSNet		57.95 104	64.26 83	50.60 125	61.62 84	65.25 105	57.18 135	45.42 82	50.79 101	26.49 178	57.81 75	60.05 93	34.51 179	71.24 66	70.20 63	78.36 67	74.44 103

viewmanbaseed2359cas		63.67 62	67.42 64	59.30 64	61.34 85	67.42 82	70.01 55	40.50 154	59.53 67	52.60 58	62.56 57	67.34 68	54.44 66	70.33 77	66.93 102	76.91 83	77.82 74

NR-MVSNet		55.35 127	59.46 122	50.56 126	61.33 86	62.97 122	57.91 131	51.80 45	48.62 125	20.59 192	51.99 102	44.73 179	34.10 182	68.58 94	68.64 79	77.66 71	70.67 124

MVS_111021_LR		63.05 66	66.43 68	59.10 65	61.33 86	63.77 118	65.87 84	43.58 115	60.20 66	53.70 54	62.09 60	62.38 80	55.84 61	70.24 78	68.08 83	74.30 118	78.28 70

MGCFI-Net		61.46 77	69.72 55	51.83 120	61.00 88	66.16 96	56.50 142	40.73 150	73.98 35	35.18 136	64.23 45	71.42 49	42.45 141	69.22 85	64.01 144	75.09 112	79.03 63

EPP-MVSNet		59.39 85	65.45 75	52.32 117	60.96 89	67.70 76	58.42 128	44.75 90	49.71 107	27.23 172	59.03 69	62.20 82	43.34 135	70.71 71	69.13 72	79.25 59	79.63 59

TransMVSNet (Re)		51.92 153	55.38 151	47.88 157	60.95 90	59.90 146	53.95 162	45.14 86	39.47 190	24.85 182	43.87 161	46.51 160	29.15 191	67.55 116	65.23 131	73.26 135	65.16 167

gm-plane-assit		44.74 191	45.95 199	43.33 179	60.88 91	46.79 205	36.97 214	32.24 204	24.15 219	11.79 209	29.26 209	32.97 214	46.64 118	65.09 152	62.95 154	71.45 156	60.42 187

baseline1		54.48 136	58.69 128	49.57 132	60.63 92	58.29 162	55.70 151	44.95 88	49.20 113	29.62 160	54.77 88	54.75 115	35.29 176	67.15 124	64.08 142	71.21 158	62.58 180

test2506		55.82 122	59.57 120	51.46 121	60.39 93	64.55 111	58.69 126	48.87 64	53.91 82	26.99 173	48.97 116	41.72 191	37.71 162	70.96 68	69.49 67	76.08 98	67.37 147

ECVR-MVS		56.44 117	60.74 99	51.42 122	60.39 93	64.55 111	58.69 126	48.87 64	53.91 82	26.76 175	45.55 148	53.43 120	37.71 162	70.96 68	69.49 67	76.08 98	67.32 149

DI_MVS_pp		61.88 72	65.17 77	58.06 71	60.05 95	65.26 103	66.03 80	44.22 97	55.75 75	46.73 77	54.64 90	68.12 64	54.13 69	69.13 87	66.66 107	77.18 79	76.61 83

PVSNet_Blended_VisFu		63.65 63	66.92 65	59.83 60	60.03 96	73.44 47	66.33 77	48.95 63	52.20 97	50.81 65	56.07 80	60.25 92	53.56 73	73.23 53	70.01 65	79.30 57	83.24 43

UniMVSNet_NR-MVSNet		56.94 112	61.14 95	52.05 119	60.02 97	65.21 106	57.44 133	52.93 40	49.37 111	24.31 185	54.62 91	50.54 133	39.04 154	68.69 91	68.84 77	78.53 64	70.72 120

IterMVS-LS		58.30 100	61.39 94	54.71 97	59.92 98	58.40 159	59.42 120	43.64 113	48.71 122	40.25 116	57.53 76	58.55 98	52.15 90	65.42 150	65.34 128	72.85 137	75.77 93
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test1111		55.24 128	59.98 113	49.71 131	59.80 99	64.10 116	56.48 143	49.34 59	52.27 96	21.56 190	44.49 156	51.96 126	35.93 174	70.59 72	69.07 73	75.13 111	67.40 145

MVS_Test		62.40 71	66.23 70	57.94 74	59.77 100	64.77 109	66.50 76	41.76 139	57.26 73	49.33 68	62.68 55	67.47 67	53.50 77	68.57 95	66.25 115	76.77 85	76.58 84

FA-MVS(training)		60.00 83	63.14 89	56.33 88	59.50 101	64.30 114	65.15 92	38.75 169	56.20 74	45.77 84	53.08 94	56.45 107	52.10 91	69.04 89	67.67 92	76.69 86	75.27 100

TranMVSNet+NR-MVSNet		55.87 120	60.14 110	50.88 124	59.46 102	63.82 117	57.93 130	52.98 39	48.94 117	20.52 193	52.87 96	47.33 151	36.81 170	69.12 88	69.03 74	77.56 75	69.89 126

Fast-Effi-MVS+		60.36 80	63.35 87	56.87 84	58.70 103	65.86 98	65.08 93	37.11 178	53.00 91	45.36 88	52.12 101	56.07 112	56.27 57	71.28 65	69.42 69	78.71 61	75.69 95

IB-MVS	54.11 11	58.36 99	60.70 100	55.62 93	58.67 104	68.02 73	61.56 107	43.15 128	46.09 142	44.06 94	44.24 158	50.99 132	48.71 107	66.70 130	70.33 60	77.60 73	78.50 67
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
Fast-Effi-MVS+-dtu		56.30 118	59.29 124	52.82 114	58.64 105	64.89 107	65.56 88	32.89 201	45.80 145	35.04 138	45.89 143	54.14 117	49.41 103	67.16 123	66.45 114	75.37 108	70.69 122

CNLPA		62.78 68	66.31 69	58.65 67	58.47 106	68.41 67	65.98 82	41.22 146	78.02 22	56.04 38	46.65 131	59.50 95	57.50 45	69.67 82	65.27 130	72.70 143	76.67 82

tpm cat1		53.30 141	53.41 164	53.17 110	58.16 107	59.15 153	63.73 103	38.27 173	50.73 102	46.98 76	45.57 147	44.00 185	49.20 104	55.90 198	54.02 197	62.65 189	64.50 171

v1144		58.88 89	60.16 109	57.39 80	58.03 108	67.26 83	67.14 69	44.46 94	45.17 148	44.33 93	47.81 125	49.92 138	53.20 83	67.77 112	66.62 110	77.15 80	76.58 84

v10		59.17 88	60.60 101	57.50 79	57.95 109	66.73 89	67.09 71	44.11 98	46.85 136	45.42 87	48.18 124	51.07 129	53.63 72	67.84 110	66.59 111	76.79 84	76.92 80

v1192		58.51 93	59.66 116	57.17 81	57.82 110	67.72 75	66.21 79	44.83 89	44.15 156	43.49 96	46.68 130	47.94 142	53.55 74	67.39 119	66.51 112	77.13 81	77.20 78

viewmambaseed2359dif		60.40 79	64.15 84	56.03 90	57.79 111	63.53 120	65.91 83	41.64 140	54.98 78	46.47 80	60.16 65	64.71 72	50.76 98	66.25 138	62.83 156	73.61 129	76.57 86

v144192		58.23 102	59.40 123	56.87 84	57.56 112	66.89 87	65.70 85	45.01 87	44.06 157	42.88 98	46.61 132	48.09 141	53.49 78	66.94 128	65.90 122	76.61 87	77.29 76

v1921920		57.89 105	59.02 126	56.58 87	57.55 113	66.66 93	64.72 96	44.70 91	43.55 161	42.73 99	46.17 140	46.93 155	53.51 75	66.78 129	65.75 124	76.29 92	77.28 77

Vis-MVSNet (Re-imp)		50.37 161	57.73 140	41.80 186	57.53 114	54.35 176	45.70 195	45.24 84	49.80 106	13.43 206	58.23 74	56.42 108	20.11 207	62.96 158	63.36 150	68.76 168	58.96 192

CostFormer		56.57 115	59.13 125	53.60 104	57.52 115	61.12 135	66.94 73	35.95 183	53.44 84	44.68 91	55.87 83	54.44 116	48.21 110	60.37 171	58.33 178	68.27 170	70.33 125

thres400		52.38 147	55.51 149	48.74 143	57.49 116	60.10 145	55.45 154	43.54 116	42.90 168	26.72 176	43.34 168	45.03 177	36.61 171	66.20 140	64.53 139	72.66 144	66.43 153

thres600view7		51.91 154	55.14 153	48.14 153	57.43 117	60.18 143	54.60 160	43.73 110	42.61 172	25.20 181	43.10 171	44.47 182	35.19 177	66.36 134	63.28 151	72.66 144	66.01 160

thres200		52.39 146	55.37 152	48.90 141	57.39 118	60.18 143	55.60 152	43.73 110	42.93 167	27.41 170	43.35 167	45.09 174	36.61 171	66.36 134	63.92 146	72.66 144	65.78 162

baseline2		55.89 119	57.82 137	53.64 103	57.36 119	61.09 136	59.75 119	40.45 155	47.38 134	41.26 110	51.23 106	46.90 156	48.11 111	65.63 147	64.38 141	74.90 114	68.16 141

v8		58.88 89	60.57 103	56.92 83	57.35 120	65.69 100	66.69 75	42.64 132	47.89 131	45.77 84	49.04 115	52.98 122	52.77 84	67.51 117	65.57 125	76.26 94	75.30 99

thres100view900		52.04 151	54.81 157	48.80 142	57.31 121	59.33 150	55.30 156	42.92 131	42.85 169	27.81 168	43.00 172	45.06 175	36.99 168	64.74 153	63.51 148	72.47 147	65.21 166

tfpn200view9		52.53 144	55.51 149	49.06 139	57.31 121	60.24 142	55.42 155	43.77 108	42.85 169	27.81 168	43.00 172	45.06 175	37.32 166	66.38 133	64.54 138	72.71 142	66.54 152

v1240		57.55 107	58.63 130	56.29 89	57.30 123	66.48 94	63.77 102	44.56 93	42.77 171	42.48 101	45.64 146	46.28 162	53.46 79	66.32 136	65.80 123	76.16 96	77.13 79

dmvs_re		52.07 149	55.11 154	48.54 148	57.27 124	51.93 185	57.73 132	43.13 129	43.65 159	26.57 177	44.52 155	50.00 137	36.53 173	66.58 132	62.15 162	69.97 164	66.91 150

CHOSEN 1792x2688		55.85 121	58.01 135	53.33 106	57.26 125	62.82 124	63.29 106	41.55 142	46.65 138	38.34 124	34.55 196	53.50 118	52.43 87	67.10 125	67.56 95	67.13 174	73.92 109

PVSNet_BlendedMVS		61.63 74	64.82 78	57.91 76	57.21 126	67.55 79	63.47 104	46.08 75	54.72 79	52.46 59	58.59 71	60.73 88	51.82 94	70.46 73	65.20 132	76.44 90	76.50 88

PVSNet_Blended		61.63 74	64.82 78	57.91 76	57.21 126	67.55 79	63.47 104	46.08 75	54.72 79	52.46 59	58.59 71	60.73 88	51.82 94	70.46 73	65.20 132	76.44 90	76.50 88

v2v482		58.69 92	60.12 112	57.03 82	57.16 128	66.05 97	67.17 68	43.52 117	46.33 140	45.19 89	49.46 114	51.02 130	52.51 86	67.30 120	66.03 119	76.61 87	74.62 102

tfpnnormal		50.16 163	52.19 175	47.78 159	56.86 129	58.37 160	54.15 161	44.01 104	38.35 198	25.94 179	36.10 191	37.89 205	34.50 180	65.93 142	63.42 149	71.26 157	65.28 165

diffmvs		61.64 73	66.55 67	55.90 91	56.63 130	63.71 119	67.13 70	41.27 145	59.49 68	46.70 78	63.93 50	68.01 65	50.46 99	67.30 120	65.51 126	73.24 136	77.87 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
HyFIR lowres test		56.87 113	58.60 131	54.84 96	56.62 131	69.27 63	64.77 95	42.21 136	45.66 146	37.50 130	33.08 199	57.47 104	53.33 80	65.46 149	67.94 85	74.60 115	71.35 117

v7n		55.67 123	57.46 142	53.59 105	56.06 132	65.29 102	61.06 113	43.26 125	40.17 187	37.99 127	40.79 181	45.27 172	47.09 117	67.67 114	66.21 116	76.08 98	76.82 81

dps		50.42 160	51.20 181	49.51 133	55.88 133	56.07 172	53.73 163	38.89 165	43.66 158	40.36 115	45.66 145	37.63 207	45.23 126	59.05 174	56.18 182	62.94 188	60.16 188

CANet_DTU		58.88 89	64.68 81	52.12 118	55.77 134	66.75 88	63.92 101	37.04 179	53.32 87	37.45 131	59.81 66	61.81 84	44.43 130	68.25 99	67.47 96	74.12 120	75.33 98

WR-MVS		48.78 173	55.06 155	41.45 187	55.50 135	60.40 141	43.77 203	49.99 56	41.92 175	8.10 219	45.24 152	45.56 167	17.47 208	61.57 166	64.60 137	73.85 122	66.14 159

UniMVSNet (Re)		55.15 132	60.39 104	49.03 140	55.31 136	64.59 110	55.77 150	50.63 52	48.66 124	20.95 191	51.47 105	50.40 134	34.41 181	67.81 111	67.89 86	77.11 82	71.88 114

test-LLR		49.28 167	50.29 185	48.10 154	55.26 137	47.16 200	49.52 176	43.48 120	39.22 191	31.98 147	43.65 164	47.93 143	41.29 147	56.80 189	55.36 188	67.08 175	61.94 181

test0.0.03 1		43.15 196	46.95 198	38.72 195	55.26 137	50.56 189	42.48 206	43.48 120	38.16 200	15.11 202	35.07 194	44.69 180	16.47 210	55.95 197	54.34 196	59.54 196	49.87 210

GA-MVS		55.67 123	58.33 132	52.58 116	55.23 139	63.09 121	61.08 112	40.15 160	42.95 166	37.02 133	52.61 98	47.68 146	47.51 115	65.92 143	65.35 127	74.49 117	70.68 123

DTE-MVSNet		48.03 179	53.28 166	41.91 185	54.64 140	57.50 168	44.63 202	51.66 48	41.02 181	7.97 220	46.26 137	40.90 193	20.24 206	60.45 170	62.89 155	72.33 150	63.97 172

pmmvs4		54.66 135	56.07 146	53.00 111	54.63 141	57.08 170	60.43 117	44.10 99	51.69 99	40.55 113	46.55 135	44.79 178	45.95 123	62.54 160	63.66 147	72.36 149	66.20 157

DU-MVS		55.41 126	59.59 117	50.54 127	54.60 142	62.97 122	57.44 133	51.80 45	48.62 125	24.31 185	51.99 102	47.00 154	39.04 154	68.11 104	67.75 90	76.03 102	70.72 120

Baseline_NR-MVSNet		53.50 139	57.89 136	48.37 151	54.60 142	59.25 152	56.10 145	51.84 44	49.32 112	17.92 200	45.38 149	47.68 146	36.93 169	68.11 104	65.95 120	72.84 138	69.57 131

v148		55.58 125	57.61 141	53.20 108	54.59 144	61.86 127	61.18 111	38.70 170	44.30 155	42.25 103	47.53 126	50.24 136	48.73 106	65.15 151	62.61 160	73.79 123	71.61 116

PEN-MVS		49.21 169	54.32 159	43.24 181	54.33 145	59.26 151	47.04 189	51.37 49	41.67 177	9.97 214	46.22 138	41.80 190	22.97 204	60.52 169	64.03 143	73.73 124	66.75 151

pm-mvs1		51.02 157	55.55 148	45.73 166	54.16 146	58.52 157	50.92 172	42.56 133	40.32 185	25.67 180	43.66 163	50.34 135	30.06 189	65.85 144	63.97 145	70.99 160	66.21 156

EPNet_dtu		52.05 150	58.26 133	44.81 172	54.10 147	50.09 192	52.01 170	40.82 149	53.03 90	27.41 170	54.90 86	57.96 103	26.72 196	62.97 157	62.70 159	67.78 172	66.19 158
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tpm		48.82 172	51.27 180	45.96 165	54.10 147	47.35 199	56.05 146	30.23 205	46.70 137	43.21 97	52.54 99	47.55 149	37.28 167	54.11 203	50.50 206	54.90 206	60.12 189

CDS-MVSNet		52.42 145	57.06 144	47.02 162	53.92 149	58.30 161	55.50 153	46.47 73	42.52 173	29.38 162	49.50 113	52.85 123	28.49 194	66.70 130	66.89 103	68.34 169	62.63 179
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test20.03		40.38 205	44.20 205	35.92 203	53.73 150	49.05 193	38.54 212	43.49 119	32.55 209	9.54 215	27.88 211	39.12 201	12.24 215	56.28 194	54.69 193	57.96 201	49.83 211

Vis-MVSNet		58.48 95	65.70 74	50.06 130	53.40 151	67.20 84	60.24 118	43.32 123	48.83 119	30.23 157	62.38 58	61.61 86	40.35 150	71.03 67	69.77 66	72.82 139	79.11 62
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PLC	52.09 14	59.21 87	62.47 90	55.41 95	53.24 152	64.84 108	64.47 99	40.41 157	65.92 54	44.53 92	46.19 139	55.69 113	55.33 63	68.24 101	65.30 129	74.50 116	71.09 118
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
thisisatest0530		56.68 114	59.68 115	53.19 109	52.97 153	60.96 138	59.41 121	40.51 152	48.26 128	41.06 111	52.67 97	46.30 161	49.78 100	67.66 115	67.83 87	75.39 107	74.07 108

OMC-MVS		65.16 59	71.35 45	57.94 74	52.95 154	68.82 64	69.00 58	38.28 172	79.89 15	55.20 43	62.76 54	68.31 61	56.14 59	71.30 64	68.70 78	76.06 101	79.67 58

tpmrst		48.08 177	49.88 189	45.98 164	52.71 155	48.11 197	53.62 166	33.70 196	48.70 123	39.74 117	48.96 117	46.23 163	40.29 151	50.14 212	49.28 208	55.80 203	57.71 195

tttt0517		56.53 116	59.59 117	52.95 112	52.66 156	60.99 137	59.21 123	40.51 152	47.89 131	40.40 114	52.50 100	46.04 165	49.78 100	67.75 113	67.83 87	75.15 110	74.17 105

GBi-Net		55.20 129	60.25 106	49.31 134	52.42 157	61.44 130	57.03 136	44.04 101	49.18 114	30.47 153	48.28 120	58.19 99	38.22 157	68.05 107	66.96 99	73.69 125	69.65 128

test1		55.20 129	60.25 106	49.31 134	52.42 157	61.44 130	57.03 136	44.04 101	49.18 114	30.47 153	48.28 120	58.19 99	38.22 157	68.05 107	66.96 99	73.69 125	69.65 128

FMVSNet2		55.04 133	59.95 114	49.31 134	52.42 157	61.44 130	57.03 136	44.08 100	49.55 108	30.40 156	46.89 129	58.84 97	38.22 157	67.07 126	66.21 116	73.69 125	69.65 128

FMVSNet3		54.78 134	59.58 119	49.17 137	52.37 160	61.31 134	56.72 141	44.04 101	49.18 114	30.47 153	48.28 120	58.19 99	38.09 160	65.48 148	65.20 132	73.31 133	69.45 136

testgi		38.71 207	43.64 207	32.95 207	52.30 161	48.63 196	35.59 217	35.05 186	31.58 213	9.03 218	30.29 204	40.75 195	11.19 221	55.30 199	53.47 202	54.53 208	45.48 214

Anonymous20231206		42.28 197	45.89 200	38.07 197	51.96 162	48.98 194	43.66 204	38.81 168	38.74 195	14.32 205	26.74 212	40.90 193	20.94 205	56.64 192	54.67 194	58.71 197	54.59 199

pmmvs6		48.35 175	51.64 177	44.51 174	51.92 163	57.94 166	49.44 178	42.17 137	34.45 205	24.62 184	28.87 210	46.90 156	29.07 193	64.60 154	63.08 152	69.83 165	65.68 163

PatchmatchNet		49.92 165	51.29 179	48.32 152	51.83 164	51.86 186	53.38 168	37.63 177	47.90 130	40.83 112	48.54 119	45.30 170	45.19 127	56.86 188	53.99 199	61.08 194	54.57 200
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
WR-MVS_H		47.65 180	53.67 162	40.63 190	51.45 165	59.74 148	44.71 201	49.37 58	40.69 183	7.61 221	46.04 141	44.34 184	17.32 209	57.79 185	61.18 166	73.30 134	65.86 161

LTVRE_ROB	44.17 16	47.06 185	50.15 188	43.44 178	51.39 166	58.42 158	42.90 205	43.51 118	22.27 221	14.85 204	41.94 179	34.57 211	45.43 124	62.28 163	62.77 158	62.56 191	68.83 139
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
CP-MVSNet		48.37 174	53.53 163	42.34 183	51.35 167	58.01 165	46.56 190	50.54 53	41.62 178	10.61 210	46.53 136	40.68 196	23.18 202	58.71 179	61.83 163	71.81 153	67.36 148

PS-CasMVS		48.18 176	53.25 167	42.27 184	51.26 168	57.94 166	46.51 191	50.52 54	41.30 179	10.56 211	45.35 151	40.34 198	23.04 203	58.66 180	61.79 164	71.74 155	67.38 146

our_test_3					51.15 169	57.31 169	55.12 157

SCA		50.99 158	53.22 168	48.40 150	51.07 170	56.78 171	50.25 174	39.05 163	48.31 127	41.38 107	49.54 112	46.70 159	46.00 122	58.31 181	56.28 181	62.65 189	56.60 197

UniMVSNet_ETH3D		52.62 143	55.98 147	48.70 145	51.04 171	60.71 140	56.87 139	46.74 72	42.52 173	26.96 174	42.50 176	45.95 166	37.87 161	66.22 139	65.15 135	72.74 140	68.78 140

IterMVS-SCA-FT		52.18 148	57.75 139	45.68 167	51.01 172	62.06 126	55.10 158	34.75 187	44.85 149	32.86 145	51.13 108	51.22 128	48.74 105	62.47 161	61.51 165	51.61 213	71.02 119

FMVSNet1		54.08 137	58.68 129	48.71 144	50.90 173	61.35 133	56.73 140	43.94 106	45.91 144	29.32 163	42.72 174	56.26 111	37.70 164	68.05 107	66.96 99	73.69 125	69.50 132

pmmvs-eth3d		51.33 155	52.25 174	50.26 129	50.82 174	54.65 175	56.03 147	43.45 122	43.51 162	37.20 132	39.20 184	39.04 202	42.28 142	61.85 165	62.78 157	71.78 154	64.72 169

MVSTER		57.19 108	61.11 96	52.62 115	50.82 174	58.79 155	61.55 108	37.86 175	48.81 120	41.31 108	57.43 78	52.10 125	48.60 108	68.19 103	66.75 105	75.56 105	75.68 96

ambc			45.54 203		50.66 176	52.63 183	40.99 209		38.36 197	24.67 183	22.62 217	13.94 227	29.14 192	65.71 146	58.06 179	58.60 199	67.43 144

thisisatest0515		53.85 138	56.84 145	50.37 128	50.25 177	58.17 163	55.99 148	39.90 161	41.88 176	38.16 126	45.91 142	45.30 170	44.58 129	66.15 141	66.89 103	73.36 132	73.57 111

baseline		55.19 131	60.88 97	48.55 147	49.87 178	58.10 164	58.70 125	34.75 187	52.82 93	39.48 122	60.18 64	60.86 87	45.41 125	61.05 167	60.74 170	63.10 187	72.41 113

MDTV_nov1_ep13		50.32 162	52.43 173	47.86 158	49.87 178	54.70 174	58.10 129	34.29 191	45.59 147	37.71 128	47.44 127	47.42 150	41.86 144	58.07 184	55.21 190	65.34 181	58.56 193

IterMVS		53.45 140	57.12 143	49.17 137	49.23 180	60.93 139	59.05 124	34.63 189	44.53 151	33.22 141	51.09 109	51.01 131	48.38 109	62.43 162	60.79 169	70.54 162	69.05 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
COLMAP_ROB	46.52 15	51.99 152	54.86 156	48.63 146	49.13 181	61.73 129	60.53 116	36.57 180	53.14 88	32.95 144	37.10 188	38.68 203	40.49 149	65.72 145	63.08 152	72.11 152	64.60 170
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CR-MVSNet		50.47 159	52.61 170	47.98 156	49.03 182	52.94 180	48.27 181	38.86 166	44.41 152	39.59 119	44.34 157	44.65 181	46.63 119	58.97 176	60.31 171	65.48 179	62.66 177

V42		56.97 111	60.14 110	53.28 107	48.16 183	62.78 125	66.30 78	37.93 174	47.44 133	42.68 100	48.19 123	52.59 124	51.90 92	67.46 118	65.94 121	72.72 141	76.55 87

MDTV_nov1_ep13_2view		47.62 181	49.72 190	45.18 170	48.05 184	53.70 178	54.90 159	33.80 195	39.90 189	29.79 159	38.85 185	41.89 189	39.17 153	58.99 175	55.55 187	65.34 181	59.17 191

EPMVS		44.66 192	47.86 196	40.92 189	47.97 185	44.70 209	47.58 186	33.27 198	48.11 129	29.58 161	49.65 111	44.38 183	34.65 178	51.71 207	47.90 210	52.49 211	48.57 212

RPMNet		46.41 186	48.72 192	43.72 176	47.77 186	52.94 180	46.02 194	33.92 193	44.41 152	31.82 150	36.89 189	37.42 208	37.41 165	53.88 204	54.02 197	65.37 180	61.47 183

TAPA-MVS	54.74 10	60.85 78	66.61 66	54.12 102	47.38 187	65.33 101	65.35 90	36.51 181	75.16 30	48.82 72	54.70 89	63.51 76	53.31 81	68.36 97	64.97 136	73.37 131	74.27 104
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SixPastTwentyTwo		47.55 182	50.25 187	44.41 175	47.30 188	54.31 177	47.81 184	40.36 158	33.76 206	19.93 195	43.75 162	32.77 215	42.07 143	59.82 172	60.94 168	68.98 166	66.37 155

TAMVS		44.02 194	49.18 191	37.99 198	47.03 189	45.97 206	45.04 198	28.47 209	39.11 193	20.23 194	43.22 170	48.52 139	28.49 194	58.15 183	57.95 180	58.71 197	51.36 203

UGNet		57.03 109	65.25 76	47.44 160	46.54 190	66.73 89	56.30 144	43.28 124	50.06 104	32.99 143	62.57 56	63.26 77	33.31 184	68.25 99	67.58 94	72.20 151	78.29 69
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
TSAR-MVS + COLMAP		62.65 69	69.90 54	54.19 100	46.31 191	66.73 89	65.49 89	41.36 144	76.57 24	46.31 81	76.80 17	56.68 105	53.27 82	69.50 83	66.65 108	72.40 148	76.36 90

PatchMatch-RL		50.11 164	51.56 178	48.43 149	46.23 192	51.94 184	50.21 175	38.62 171	46.62 139	37.51 129	42.43 177	39.38 200	52.24 89	60.98 168	59.56 174	65.76 178	60.01 190

CMPMVS	37.70 17	49.24 168	52.71 169	45.19 169	45.97 193	51.23 188	47.44 187	29.31 206	43.04 165	44.69 90	34.45 197	48.35 140	43.64 132	62.59 159	59.82 173	60.08 195	69.48 133
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmnet_mix02		40.48 204	43.80 206	36.61 201	45.79 194	40.45 214	42.12 207	33.18 199	40.30 186	24.11 187	38.76 186	37.11 209	24.30 200	52.97 205	46.66 214	50.17 214	50.33 207

pmmvs5		47.07 184	51.02 183	42.46 182	45.18 195	51.47 187	48.23 183	33.09 200	38.17 199	28.62 166	46.60 133	43.48 186	30.74 187	58.28 182	58.63 177	68.92 167	60.48 186

USDC		51.11 156	53.71 161	48.08 155	44.76 196	55.99 173	53.01 169	40.90 147	52.49 94	36.14 134	44.67 154	33.66 213	43.27 137	63.23 156	61.10 167	70.39 163	64.82 168

FC-MVSNet-test		39.65 206	48.35 194	29.49 210	44.43 197	39.28 218	30.23 220	40.44 156	43.59 160	3.12 227	53.00 95	42.03 188	10.02 223	55.09 200	54.77 192	48.66 215	50.71 205

ADS-MVSNet		40.67 202	43.38 208	37.50 199	44.36 198	39.79 216	42.09 208	32.67 203	44.34 154	28.87 165	40.76 182	40.37 197	30.22 188	48.34 217	45.87 215	46.81 217	44.21 216

new-patchmatchnet		33.24 213	37.20 214	28.62 212	44.32 199	38.26 219	29.68 221	36.05 182	31.97 211	6.33 223	26.59 213	27.33 218	11.12 222	50.08 213	41.05 218	44.23 218	45.15 215

MVS-HIRNet		42.24 198	41.15 211	43.51 177	44.06 200	40.74 212	35.77 216	35.35 184	35.38 204	38.34 124	25.63 214	38.55 204	43.48 134	50.77 209	47.03 212	64.07 183	49.98 208

PatchT		48.08 177	51.03 182	44.64 173	42.96 201	50.12 191	40.36 210	35.09 185	43.17 164	39.59 119	42.00 178	39.96 199	46.63 119	58.97 176	60.31 171	63.21 186	62.66 177

CVMVSNet		46.38 188	52.01 176	39.81 192	42.40 202	50.26 190	46.15 192	37.68 176	40.03 188	15.09 203	46.56 134	47.56 148	33.72 183	56.50 193	55.65 186	63.80 185	67.53 143

TinyColmap		47.08 183	47.56 197	46.52 163	42.35 203	53.44 179	51.77 171	40.70 151	43.44 163	31.92 149	29.78 207	23.72 223	45.04 128	61.99 164	59.54 175	67.35 173	61.03 184

ET-MVSNet_ETH3D		58.38 98	61.57 93	54.67 98	42.15 204	65.26 103	65.70 85	43.82 107	48.84 118	42.34 102	59.76 67	47.76 145	56.68 54	67.02 127	68.60 81	77.33 78	73.73 110

MIMVSNet		43.79 195	48.53 193	38.27 196	41.46 205	48.97 195	50.81 173	32.88 202	44.55 150	22.07 188	32.05 200	47.15 152	24.76 199	58.73 178	56.09 184	57.63 202	52.14 201

WB-MVS		29.70 215	35.40 216	23.05 215	40.96 206	39.59 217	18.79 224	40.20 159	25.26 217	1.88 230	33.33 198	21.97 225	3.36 224	48.69 216	44.60 216	33.11 222	34.39 218

N_pmnet		32.67 214	36.85 215	27.79 213	40.55 207	32.13 220	35.80 215	26.79 212	37.24 202	9.10 216	32.02 201	30.94 216	16.30 211	47.22 218	41.21 217	38.21 220	37.21 217

anonymousdsp		52.84 142	57.78 138	47.06 161	40.24 208	58.95 154	53.70 164	33.54 197	36.51 203	32.69 146	43.88 160	45.40 168	47.97 114	67.17 122	70.28 61	74.22 119	82.29 47

EU-MVSNet		40.63 203	45.65 202	34.78 206	39.11 209	46.94 203	40.02 211	34.03 192	33.50 207	10.37 212	35.57 193	37.80 206	23.65 201	51.90 206	50.21 207	61.49 193	63.62 175

FPMVS		38.36 208	40.41 212	35.97 202	38.92 210	39.85 215	45.50 196	25.79 215	41.13 180	18.70 197	30.10 205	24.56 221	31.86 186	49.42 214	46.80 213	55.04 204	51.03 204

TESTMET0.1,1		46.09 189	50.29 185	41.18 188	36.91 211	47.16 200	49.52 176	20.32 219	39.22 191	31.98 147	43.65 164	47.93 143	41.29 147	56.80 189	55.36 188	67.08 175	61.94 181

FMVSNet5		40.96 200	45.81 201	35.29 205	34.30 212	44.55 210	47.28 188	28.84 208	40.76 182	21.62 189	29.85 206	42.44 187	24.77 198	57.53 186	55.00 191	54.93 205	50.56 206

PMMVS		49.20 170	54.28 160	43.28 180	34.13 213	45.70 207	48.98 179	26.09 214	46.31 141	34.92 140	55.22 85	53.47 119	47.48 116	59.43 173	59.04 176	68.05 171	60.77 185

PMVS	27.84 18	33.81 212	35.28 217	32.09 208	34.13 213	24.81 223	32.51 219	26.48 213	26.41 216	19.37 196	23.76 215	24.02 222	25.18 197	50.78 208	47.24 211	54.89 207	49.95 209
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test-mter		45.30 190	50.37 184	39.38 193	33.65 215	46.99 202	47.59 185	18.59 220	38.75 194	28.00 167	43.28 169	46.82 158	41.50 146	57.28 187	55.78 185	66.93 177	63.70 174

CHOSEN 280x420		40.80 201	45.05 204	35.84 204	32.95 216	29.57 221	44.98 199	23.71 217	37.54 201	18.42 198	31.36 203	47.07 153	46.41 121	56.71 191	54.65 195	48.55 216	58.47 194

PM-MVS		44.55 193	48.13 195	40.37 191	32.85 217	46.82 204	46.11 193	29.28 207	40.48 184	29.99 158	39.98 183	34.39 212	41.80 145	56.08 196	53.88 201	62.19 192	65.31 164

TDRefinement		49.31 166	52.44 172	45.67 168	30.44 218	59.42 149	59.24 122	39.78 162	48.76 121	31.20 152	35.73 192	29.90 217	42.81 140	64.24 155	62.59 161	70.55 161	66.43 153

Gipuma		25.87 216	26.91 219	24.66 214	28.98 219	20.17 224	20.46 222	34.62 190	29.55 214	9.10 216	4.91 227	5.31 231	15.76 212	49.37 215	49.10 209	39.03 219	29.95 220
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDA-MVSNet-bldmvs		41.36 199	43.15 209	39.27 194	28.74 220	52.68 182	44.95 200	40.84 148	32.89 208	18.13 199	31.61 202	22.09 224	38.97 156	50.45 211	56.11 183	64.01 184	56.23 198

E-PMN		15.09 219	13.19 223	17.30 217	27.80 221	12.62 227	7.81 228	27.54 210	14.62 225	3.19 225	6.89 224	2.52 234	15.09 213	15.93 223	20.22 222	22.38 223	19.53 223

MIMVSNet1		35.51 210	41.41 210	28.63 211	27.53 222	43.36 211	38.09 213	33.82 194	32.01 210	6.77 222	21.63 218	35.43 210	11.97 217	55.05 201	53.99 199	53.59 210	48.36 213

EMVS		14.49 220	12.45 224	16.87 219	27.02 223	12.56 228	8.13 227	27.19 211	15.05 224	3.14 226	6.69 225	2.67 233	15.08 214	14.60 225	18.05 223	20.67 224	17.56 225

pmmvs3		35.10 211	38.47 213	31.17 209	26.37 224	40.47 213	34.51 218	18.09 221	24.75 218	16.88 201	23.05 216	26.69 219	32.69 185	50.73 210	51.60 204	58.46 200	51.98 202

RPSCF		46.41 186	54.42 158	37.06 200	25.70 225	45.14 208	45.39 197	20.81 218	62.79 60	35.10 137	44.92 153	55.60 114	43.56 133	56.12 195	52.45 203	51.80 212	63.91 173

new_pmnet		23.19 217	28.17 218	17.37 216	17.03 226	24.92 222	19.66 223	16.16 223	27.05 215	4.42 224	20.77 219	19.20 226	12.19 216	37.71 219	36.38 219	34.77 221	31.17 219

PMMVS2		15.84 218	19.68 220	11.35 220	15.74 227	16.95 225	13.31 225	17.64 222	16.08 223	0.36 231	13.12 221	11.47 228	1.69 226	28.82 220	27.24 221	19.38 226	24.09 222

MVE	12.28 19	13.53 221	15.72 221	10.96 221	7.39 228	15.71 226	6.05 229	23.73 216	10.29 227	3.01 228	5.77 226	3.41 232	11.91 218	20.11 221	29.79 220	13.67 227	24.98 221
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				5.40 223	3.97 229	2.35 231	3.26 231	0.44 226	17.56 222	12.09 207	11.48 223	7.14 229	1.98 225	15.68 224	15.49 224	10.69 228

test_method		12.44 222	14.66 222	9.85 222	1.30 230	3.32 230	13.00 226	3.21 224	22.42 220	10.22 213	14.13 220	25.64 220	11.43 220	19.75 222	11.61 225	19.96 225	5.79 226

GG-mvs-BLEND		36.62 209	53.39 165	17.06 218	0.01 231	58.61 156	48.63 180	0.01 227	47.13 135	0.02 232	43.98 159	60.64 90	0.03 227	54.92 202	51.47 205	53.64 209	56.99 196

uanet_test		0.00 225	0.00 227	0.00 224	0.00 232	0.00 232	0.00 234	0.00 228	0.00 230	0.00 233	0.00 230	0.00 235	0.00 230	0.00 228	0.00 228	0.00 230	0.00 229

sosnet-low-res		0.00 225	0.00 227	0.00 224	0.00 232	0.00 232	0.00 234	0.00 228	0.00 230	0.00 233	0.00 230	0.00 235	0.00 230	0.00 228	0.00 228	0.00 230	0.00 229

sosnet		0.00 225	0.00 227	0.00 224	0.00 232	0.00 232	0.00 234	0.00 228	0.00 230	0.00 233	0.00 230	0.00 235	0.00 230	0.00 228	0.00 228	0.00 230	0.00 229

testmvs		0.01 223	0.02 225	0.00 224	0.00 232	0.00 232	0.01 233	0.00 228	0.01 228	0.00 233	0.03 229	0.00 235	0.01 228	0.01 227	0.01 226	0.00 230	0.06 228

test123		0.01 223	0.02 225	0.00 224	0.00 232	0.00 232	0.00 234	0.00 228	0.01 228	0.00 233	0.04 228	0.00 235	0.01 228	0.00 228	0.01 226	0.00 230	0.07 227

RE-MVS-def										33.01 142

9.14												81.81 13

MTAPA										65.14 4		80.20 20

MTMP										62.63 16		78.04 27

Patchmatch-RL test							1.04 232

NP-MVS									72.00 42

Patchmtry						47.61 198	48.27 181	38.86 166		39.59 119

DeepMVS_CX						6.95 229	5.98 230	2.25 225	11.73 226	2.07 229	11.85 222	5.43 230	11.75 219	11.40 226		8.10 229	18.38 224

High-resolution multi-view benchmark