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

Abstract

In this paper, we introduce a local image descriptor, DAISY, which is very efficient to compute densely. We also present an EM-based algorithm to compute dense depth and occlusion maps from wide-baseline image pairs using this descriptor. This yields much better results in wide-baseline situations than the pixel and correlation-based algorithms that are commonly used in narrow-baseline stereo. Also, using a descriptor makes our algorithm robust against many photometric and geometric transformations. Our descriptor is inspired from earlier ones such as SIFT and GLOH but can be computed much faster for our purposes. Unlike SURF, which can also be computed efficiently at every pixel, it does not introduce artifacts that degrade the matching performance when used densely. It is important to note that our approach is the first algorithm that attempts to estimate dense depth maps from wide-baseline image pairs, and we show that it is a good one at that with many experiments for depth estimation accuracy, occlusion detection, and comparing it against other descriptors on laser-scanned ground truth scenes. We also tested our approach on a variety of indoor and outdoor scenes with different photometric and geometric transformations and our experiments support our claim to being robust against these.

A survey on face detection in the wild: Past, present and future

“…In particular, generative DPMs, as in [47], can be trained very fast (even real time). The state-of-the-art discriminatively trained DPMs require to solve (a) an optimization problem like (24) which alternates between the model parameters and part locations (weakly supervised) or (b) an optimization problem like (25) where only the optimal model parameters need to be recovered, since the part locations are provided (strongly supervised). The computational complexity of these optimization problems depends on the number of training samples but generally it is feasible to train a model with thousands of training samples in few hours.…”

“…• The introduction of robust feature extraction methodologies, such as Scale Invariant Feature Transform (SIFT) features [18], Histograms of oriented Gradients (HoGs) [19], Local Binary Patterns (LBPs) and their variations [20,21,22], their fast counterparts such as Speeded Up Robust Features (SURF) [23] and DAISY [24], as well as transformations that combine the above features with integral images, such as Integral Channel Features (ICF) [25,26]. These features are densely or sparsely sampled and are used to describe face appearance.…”

Learning Deep Relationship for Object Detection

“…For these three approaches, DAISY [13] feature is used since it's a fast dense local image feature descriptor. D-SVM is used to learn the shallow relationship by a single-layer architecture, while Fk-SVM trains SVM to learn the local spatial relationship.…”

An optimisation approach to the design of a fast, compact and distinctive binary descriptor

“…The pairwise tests are performed only between some cells. It is worth mentioning that BRISK descriptor was also inspired by the dense approach (DAISY [26]). MBLBP uses only three image patches, and their sizes are given in pixels.…”