DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo

By Engin Tola, Vincent Lepetit, Pascal Fua. 2010

1,558 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

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

Citations in the corpus

Colorful Image Colorization (2016, background): “[1] learn a 3-layer neural network from the concatenation of patches, DAISY features [12], and the output of an FCN [13] on 47 pre-defined classes.”
Scattering Networks for Hybrid Representation Learning (2018, background): “proposed descriptors [54], a Scattering Network can avoid discarding information.”
Learning Spread-Out Local Feature Descriptors (2017, background): “One of the most popular hand-crafted descriptors is SIFT [10] and its variants [2, 24], which are widely used in the computer vision community.”
Invariant Scattering Convolution Networks (2012, methodology): “The output of the ﬁrst network layer is similar to SIFT [21] or Daisy [33] type descriptors.”
#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning (2016, methodology): “However, it is designed for generic Atari game images and may not capture the structure of each speciﬁc game very well.”
Comparative Evaluation of Binary Features (2012, result): “This may seem similar to the DAISY descriptor [20], but the authors point out that DAISY was designed specifically for dense matching, and captures more information than is needed for keypoint description.”
Hierarchical Deep Stereo Matching on High-Resolution Images (2019, methodology): “Traditional methods take rectified image pairs as input (though extensions to multiview stereo exist [32]), extract local descriptors at candidate patches [35, 36] and then build up 3-dimensional cost volumes across corresponding epipolar scanlines [22].”
Neural best-buddies (2018, background): “2006] and Daisy [Tola et al. 2010], has brought significant progress to a wide range of matching-based applications.”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Gradient Response Maps for Real-time Detection of Texture-less Objects (background): “Another option is to apply Gaussian convolution to the orientations like in DAISY [31], but this would be too slow for our purpose.”
Local Intensity Order Pattern for feature description (2011, background): “We have compared our descriptor with SIFT [13], DAISY [23] and HRI-CSLTP [9] since SIFT and DAISY are the well known state-of-the-art feature descriptors while HRI-CSLTP is the recently proposed order based descriptor similar to ours.”
Learning to Match Aerial Images with Deep Attentive Architectures (2016, background): “Numerous de- scriptors have been developed within the community, such as SURF [5], BRIEF [8], and DAISY [36].”
Median Robust Extended Local Binary Pattern for Texture Classification (2016, methodology): “mation, inspired by DAISY [23], BRISK [24] and FREAK [25].”
Feature representation for statistical-learning-based object detection: A review (2015, background): “Categories Typical feature representation methods Engineering -based features Gradient features SIFT [2], PCA-SIFT(1) [3], RIFT [4], GLOH(1) [5], SURF [6], DAISY [7], GIST(1) [8], RIFF [9], WLD [10], HOG [11][12], integral histogram [13], v-HoG [14][15], CoHOG [16], spHOG [17], PQ-HOG [18], WHO(1) [”
A data driven method for feature transformation (2012, methodology): “Inspired by Scale Invariant Feature Transform (SIFT [21]), which was originally intended for resolving the problem of keypoint correspondence, many variants have been proposed improving on computational efficiency[15, 4] and invariance properties [24].”
A Survey of Augmented Reality (2015, background): “, 2010] and a feature descriptor inspired by DAISY [Tola et al., 2010], and FREAK [Alahi et al.”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “1999; Lowe 2004) and its improvement versions (Bay et al. 2006; Morel and Yu 2009; Dong and Soatto 2015; Tola et al. 2010), and they are still widely used in several modern visual tasks.”