On benchmarking camera calibration and multi-view stereo for high resolution imagery

By Christoph Strecha, Wolfgang von Hansen, Luc Van Gool, Pascal Fua, Ulrich Thoennessen. 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008

926 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/dd0ccfd5940693cf6f417bd429356ea74e7bb647

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

A fast local descriptor for dense matching (2008, methodology): “To compare DAISY against that of other descriptors, we used the images [26, 23] of Fig.”
Assessing the Accuracy of Georeferenced Point Clouds Produced via Multi-View Stereopsis from Unmanned Aerial Vehicle (UAV) Imagery (2012, methodology): “[31] used LiDAR reference data to compare the Furukawa and Ponce [4] approach to the Strecha and Fransens [32] and Strecha et al.”
High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth (2014, background): “Existing two-view [7] and multiview [30, 31] stereo datasets for which the ground truth was obtained with a laser scanner typically suffer from (1) limited ground-truth resolution and coverage; and (2) limited precision of the calibration relating ground-truth model and input images.”
A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos (2017, methodology): “[40] proposed a new MVS benchmark comprising 6 outdoor datasets which include ∼30 images at 6 Megapixel resolution, as well as ground truth 3D models captured by a laser scanner.”
Pixelwise View Selection for Unstructured Multi-View Stereo (2016, methodology): “Strecha benchmark [20] with reported values from [60].”
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance (2020, methodology): “We further tested our method on the Fountain-P11 image collections [43] provided with 11 high resolution images with associated GT camera parameters.”
LDAHash: Improved Matching with Smaller Descriptors (2012, methodology): “We evaluated the performance of our binarized descriptor on publicly available data sets [41], [38], for which camera parameters and the ground truth 3D model are available.”
Dense Semantic 3D Reconstruction (2017, methodology): “We use the dataset Castle P-30 from [37] and three additional urban datasets (Southbuilding, Providence and Catania).”
A Survey on Structure from Motion (2017, background): “…early work providing several benchmark datasets (now considered to have small sizes) including high resolution images, intrinsic camera parameters, ground truth camera motion and resulting dense 3D constructions, is [69] (datasets are available at http://cvlabwww.epfl.ch/data/multiview/ ).”
Accurate, Dense, and Robust Multi-View Stereopsis (2007, background): “provide quantitative evaluations for two scene datasets, fountain and herzjesu [35], [36] (see Table III).”
Tanks and temples (2017, methodology): “The EPFL benchmark of Strecha et al. [2008] used building fa-cades and was acquired outside the lab.”
LIFT: Learned Invariant Feature Transform (2016, background): “The Strecha dataset [30], which contains 19 images of two scenes seen from increasingly diﬀerent viewpoints.”
Image Matching from Handcrafted to Deep Features: A Survey (2020, background): “For instance, the early reviews (Zitova and Flusser 2003; Tuytelaars and Mikolajczyk 2008; Strecha et al. 2008; Aanæs et al. 2012; Heinly et al. 2012; Awrangjeb et al. 2012; Li et al. 2015) typically focus on handcrafted methods, which are not sufficient to provide a valuable reference for…”
Learning to Find Good Correspondences (2017, neutral): “We also consider the ‘Fountain’ and ‘HerzJesu’ sequences from [27].”
BRIEF: Computing a Local Binary Descriptor Very Fast (2012, neutral): “ch/~strecha/multiview [39] http://cvlab.”
Robust Probabilistic Occupancy Grid Estimation from Positive and Negative Distance Fields (2012, methodology): “In this section, we present an evaluation of our algorithm on two real outdoor datasets with ground truth [30].”
Comparative Evaluation of Binary Features (2012, methodology): “[12] published a dense 3D dataset, which we use in our evaluation as it provides 3D LIDAR-based geometry and camera poses.”