This paper investigates into the colorization problem which converts a grayscale image to a colorful version. This is a very difficult problem and normally requires manual adjustment to achieve artifact-free quality. For instance, it normally requires human-labelled color scribbles on the grayscale target image or a careful selection of colorful reference images (e.g., capturing the same scene in the grayscale target image). Unlike the previous methods, this paper aims at a high-quality fully-automatic colorization method. With the assumption of a perfect patch matching technique, the use of an extremely large-scale reference database (that contains sufficient color images) is the most reliable solution to the colorization problem. However, patch matching noise will increase with respect to the size of the reference database in practice. Inspired by the recent success in deep learning techniques which provide amazing modeling of large-scale data, this paper re-formulates the colorization problem so that deep learning techniques can be directly employed. To ensure artifact-free quality, a joint bilateral filtering based post-processing step is proposed. We further develop an adaptive image clustering technique to incorporate the global image information. Numerous experiments demonstrate that our method outperforms the state-of-art algorithms both in terms of quality and speed.
We present a new smooth, Gaussian-like kernel that allows the kernel density estimate for an angular distribution to be exactly represented by a finite number of its Fourier series coefficients. Distributions of angular quantities, such as gradients, are a central part of several state-of-the-art image processing algorithms, but these distributions are usually described via histograms and therefore lack rotation invariance due to binning artifacts. Replacing histograming with kernel density estimation removes these binning artifacts and can provide a finite-dimensional descriptor of the distribution, provided that the kernel is selected to be bandlimited. In this paper, we present a new band-limited kernel that has the added advantage of being Gaussian-like in the angular domain. We then show that it compares favorably to gradient histograms for patch matching, person detection, and texture segmentation.
The focus of our work is speeding up evaluation of deep neural networks in retrieval scenarios, where conventional architectures may spend too much time on negative examples. We propose to replace a monolithic network with our novel cascade of feature-sharing deep classifiers, called OnionNet, where subsequent stages may add both new layers as well as new feature channels to the previous ones. Importantly, intermediate feature maps are shared among classifiers, preventing them from the necessity of being recomputed. To accomplish this, the model is trained end-to-end in a principled way under a joint loss. We validate our approach in theory and on a synthetic benchmark. As a result demonstrated in three applications (patch matching, object detection, and image retrieval), our cascade can operate significantly faster than both monolithic networks and traditional cascades without sharing at the cost of marginal decrease in precision.
Image and texture synthesis is a challenging task that has long been drawing attention in the fields of image processing, graphics, and machine learning. This problem consists of modelling the desired type of images, either through training examples or via a parametric modeling, and then generating images that belong to the same statistical origin. This work addresses the image synthesis task, focusing on two specific families of images -- handwritten digits and face images. This paper offers two main contributions. First, we suggest a simple and intuitive algorithm capable of generating such images in a unified way. The proposed approach taken is pyramidal, consisting of upscaling and refining the estimated image several times. For each upscaling stage, the algorithm randomly draws small patches from a patch database, and merges these to form a coherent and novel image with high visual quality. The second contribution is a general framework for the evaluation of the generation performance, which combines three aspects: the likelihood, the originality and the spread of the synthesized images. We assess the proposed synthesis scheme and show that the results are similar in nature, and yet different from the ones found in the training set, suggesting that true synthesis effect has been obtained.
We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches. This is in contrast to previous person re-id works, which rely on either single frame based person to person patch matching, or graph based sequence to sequence matching. We show that a progressive/sequential fusion framework based on long short term memory (LSTM) network aggregates the frame-wise human region representation at each time stamp and yields a sequence level human feature representation. Since LSTM nodes can remember and propagate previously accumulated good features and forget newly input inferior ones, even with simple hand-crafted features, the proposed recurrent feature aggregation network (RFA-Net) is effective in generating highly discriminative sequence level human representations. Extensive experimental results on two person re-identification benchmarks demonstrate that the proposed method performs favorably against state-of-the-art person re-identification methods.
Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being dense, they have the major disadvantage of being very outlier-prone as they are not designed to find the optical flow, but the visually most similar correspondence. In this article we present a dense correspondence field approach that is much less outlier-prone and thus much better suited for optical flow estimation than approximate nearest neighbor fields. Our approach does not require explicit regularization, smoothing (like median filtering) or a new data term. Instead we solely rely on patch matching techniques and a novel multi-scale matching strategy. We also present enhancements for outlier filtering. We show that our approach is better suited for large displacement optical flow estimation than modern descriptor matching techniques. We do so by initializing EpicFlow with our approach instead of their originally used state-of-the-art descriptor matching technique. We significantly outperform the original EpicFlow on MPI-Sintel, KITTI 2012, KITTI 2015 and Middlebury. In this extended article of our former conference publication we further improve our approach in matching accuracy as well as runtime and present more experiments and insights.
This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair. The learned correspondence structure can not only capture the spatial correspondence pattern between cameras but also handle the viewpoint or human-pose variation in individual images. We further introduce a global constraint-based matching process. It integrates a global matching constraint over the learned correspondence structure to exclude cross-view misalignments during the image patch matching process, hence achieving a more reliable matching score between images. Finally, we also extend our approach by introducing a multi-structure scheme, which learns a set of local correspondence structures to capture the spatial correspondence sub-patterns between a camera pair, so as to handle the spatial misalignments between individual images in a more precise way. Experimental results on various datasets demonstrate the effectiveness of our approach.
Learning based approaches have not yet achieved their full potential in optical flow estimation, where their performance still trails heuristic approaches. In this paper, we present a CNN based patch matching approach for optical flow estimation. An important contribution of our approach is a novel thresholded loss for Siamese networks. We demonstrate that our loss performs clearly better than existing losses. It also allows to speed up training by a factor of 2 in our tests. Furthermore, we present a novel way for calculating CNN based features for different image scales, which performs better than existing methods. We also discuss new ways of evaluating the robustness of trained features for the application of patch matching for optical flow. An interesting discovery in our paper is that low-pass filtering of feature maps can increase the robustness of features created by CNNs. We proved the competitive performance of our approach by submitting it to the KITTI 2012, KITTI 2015 and MPI-Sintel evaluation portals where we obtained state-of-the-art results on all three datasets.
Recovering surgical scene structure in laparoscope surgery is crucial step for surgical guidance and augmented reality applications. In this paper, a quasi dense reconstruction algorithm of surgical scene is proposed. This is based on a state-of-the-art SLAM system, and is exploiting the initial exploration phase that is typically performed by the surgeon at the beginning of the surgery. We show how to convert the sparse SLAM map to a quasi dense scene reconstruction, using pairs of keyframe images and correlation-based featureless patch matching. We have validated the approach with a live porcine experiment using Computed Tomography as ground truth, yielding a Root Mean Squared Error of 4.9mm.
Although the recent progress in the deep neural network has led to the development of learnable local feature descriptors, there is no explicit answer for estimation of the necessary size of a neural network. Specifically, the local feature is represented in a low dimensional space, so the neural network should have more compact structure. The small networks required for local feature descriptor learning may be sensitive to initial conditions and learning parameters and more likely to become trapped in local minima. In order to address the above problem, we introduce an adaptive pruning Siamese Architecture based on neuron activation to learn local feature descriptors, making the network more computationally efficient with an improved recognition rate over more complex networks. Our experiments demonstrate that our learned local feature descriptors outperform the state-of-art methods in patch matching.
Volumetric (3d) images are acquired for many scientific and biomedical purposes using imaging methods such as serial section microscopy, CT scans, and MRI. A frequent step in the analysis and reconstruction of such data is the alignment and registration of images that were acquired in succession along a spatial or temporal dimension. For example, in serial section electron microscopy, individual 2d sections are imaged via electron microscopy and then must be aligned to one another in order to produce a coherent 3d volume. State of the art approaches find image correspondences derived from patch matching and invariant feature detectors, and then solve optimization problems that rigidly or elastically deform series of images into an aligned volume. Here we show how fully convolutional neural networks trained with an adversarial loss function can be used for two tasks: (1) synthesis of missing or damaged image data from adjacent sections, and (2) fine-scale alignment of block-face electron microscopy data. Finally, we show how these two capabilities can be combined in order to produce artificial isotropic volumes from anisotropic image volumes using a super-resolution adversarial alignment and interpolation approach.
We propose a convolutional neural network (ConvNet) based approach for learning local image descriptors which can be used for significantly improved patch matching and 3D reconstructions. A multi-resolution ConvNet is used for learning keypoint descriptors. We also propose a new dataset consisting of an order of magnitude more number of scenes, images, and positive and negative correspondences compared to the currently available Multi-View Stereo (MVS) [18] dataset. The new dataset also has better coverage of the overall viewpoint, scale, and lighting changes in comparison to the MVS dataset. We evaluate our approach on publicly available datasets, such as Oxford Affine Covariant Regions Dataset (ACRD) [12], MVS [18], Synthetic [6] and Strecha [15] datasets to quantify the image descriptor performance. Scenes from the Oxford ACRD, MVS and Synthetic datasets are used for evaluating the patch matching performance of the learnt descriptors while the Strecha dataset is used to evaluate the 3D reconstruction task. Experiments show that the proposed descriptor outperforms the current state-of-the-art descriptors in both the evaluation tasks.
In many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image. If this relationship is explicitly encoded, instead of treated as any other variation, the complexity of the problem is decreased, leading to a reduction in the size of the required model. In this paper, we propose the Rotation Equivariant Vector Field Networks (RotEqNet), a Convolutional Neural Network (CNN) architecture encoding rotation equivariance, invariance and covariance. Each convolutional filter is applied at multiple orientations and returns a vector field representing magnitude and angle of the highest scoring orientation at every spatial location. We develop a modified convolution operator relying on this representation to obtain deep architectures. We test RotEqNet on several problems requiring different responses with respect to the inputs' rotation: image classification, biomedical image segmentation, orientation estimation and patch matching. In all cases, we show that RotEqNet offers extremely compact models in terms of number of parameters and provides results in line to those of networks orders of magnitude larger.
Matching sonar images with high accuracy has been a problem for a long time, as sonar images are inherently hard to model due to reflections, noise and viewpoint dependence. Autonomous Underwater Vehicles require good sonar image matching capabilities for tasks such as tracking, simultaneous localization and mapping (SLAM) and some cases of object detection/recognition. We propose the use of Convolutional Neural Networks (CNN) to learn a matching function that can be trained from labeled sonar data, after pre-processing to generate matching and non-matching pairs. In a dataset of 39K training pairs, we obtain 0.91 Area under the ROC Curve (AUC) for a CNN that outputs a binary classification matching decision, and 0.89 AUC for another CNN that outputs a matching score. In comparison, classical keypoint matching methods like SIFT, SURF, ORB and AKAZE obtain AUC 0.61 to 0.68. Alternative learning methods obtain similar results, with a Random Forest Classifier obtaining AUC 0.79, and a Support Vector Machine resulting in AUC 0.66.
We present an accurate stereo matching method using local expansion moves based on graph cuts. This new move-making scheme is used to efficiently infer per-pixel 3D plane labels on a pairwise Markov random field (MRF) that effectively combines recently proposed slanted patch matching and curvature regularization terms. The local expansion moves are presented as many alpha-expansions defined for small grid regions. The local expansion moves extend traditional expansion moves by two ways: localization and spatial propagation. By localization, we use different candidate alpha-labels according to the locations of local alpha-expansions. By spatial propagation, we design our local alpha-expansions to propagate currently assigned labels for nearby regions. With this localization and spatial propagation, our method can efficiently infer MRF models with a continuous label space using randomized search. Our method has several advantages over previous approaches that are based on fusion moves or belief propagation; it produces submodular moves deriving a subproblem optimality; it helps find good, smooth, piecewise linear disparity maps; it is suitable for parallelization; it can use cost-volume filtering techniques for accelerating the matching cost computations. Even using a simple pairwise MRF, our method is shown to have best performance in the Middlebury stereo benchmark V2 and V3.
In this work we propose a neural network based image descriptor suitable for image patch matching, which is an important task in many computer vision applications. Our approach is influenced by recent success of deep convolutional neural networks (CNNs) in object detection and classification tasks. We develop a model which maps the raw input patch to a low dimensional feature vector so that the distance between representations is small for similar patches and large otherwise. As a distance metric we utilize L2 norm, i.e. Euclidean distance, which is fast to evaluate and used in most popular hand-crafted descriptors, such as SIFT. According to the results, our approach outperforms state-of-the-art L2-based descriptors and can be considered as a direct replacement of SIFT. In addition, we conducted experiments with batch normalization and histogram equalization as a preprocessing method of the input data. The results confirm that these techniques further improve the performance of the proposed descriptor. Finally, we show promising preliminary results by appending our CNNs with recently proposed spatial transformer networks and provide a visualisation and interpretation of their impact.
We introduce a novel loss for learning local feature descriptors which is inspired by the Lowe's matching criterion for SIFT. We show that the proposed loss that maximizes the distance between the closest positive and closest negative patch in the batch is better than complex regularization methods; it works well for both shallow and deep convolution network architectures. Applying the novel loss to the L2Net CNN architecture results in a compact descriptor -- it has the same dimensionality as SIFT (128) that shows state-of-art performance in wide baseline stereo, patch verification and instance retrieval benchmarks. It is fast, computing a descriptor takes about 1 millisecond on a low-end GPU.
We propose a new dataset for learning local image descriptors which can be used for significantly improved patch matching. Our proposed dataset consists of an order of magnitude more number of scenes, images, and positive and negative correspondences compared to the currently available Multi-View Stereo (MVS) dataset from Brown et al. The new dataset also has better coverage of the overall viewpoint, scale, and lighting changes in comparison to the MVS dataset. Our dataset also provides supplementary information like RGB patches with scale and rotations values, and intrinsic and extrinsic camera parameters which as shown later can be used to customize training data as per application. We train an existing state-of-the-art model on our dataset and evaluate on publicly available benchmarks such as HPatches dataset and Strecha et al.\cite{strecha} to quantify the image descriptor performance. Experimental evaluations show that the descriptors trained using our proposed dataset outperform the current state-of-the-art descriptors trained on MVS by 8%, 4% and 10% on matching, verification and retrieval tasks respectively on the HPatches dataset. Similarly on the Strecha dataset, we see an improvement of 3-5% for the matching task in non-planar scenes.
Multimodal patch matching addresses the problem of finding the correspondences between image patches from two different modalities, e.g. RGB vs sketch or RGB vs near-infrared. The comparison of patches of different modalities can be done by discovering the information common to both modalities (Siamese like approaches) or the modality-specific information (Pseudo-Siamese like approaches). We observed that none of these two scenarios is optimal. This motivates us to propose a three-stream architecture, dubbed as TS-Net, combining the benefits of the two. In addition, we show that adding extra constraints in the intermediate layers of such networks further boosts the performance. Experimentations on three multimodal datasets show significant performance gains in comparison with Siamese and Pseudo-Siamese networks.
Image patch matching, which is the process of identifying corresponding patches across images, has been used as a subroutine for many computer vision and image processing tasks. State -of-the-art patch matching techniques take image patches as input to a convolutional neural network to extract the patch features and evaluate their similarity. Our aim in this paper is to improve on the state of the art patch matching techniques by observing the fact that a sparse-overcomplete representation of an image posses statistical properties of natural visual scenes which can be exploited for patch matching. We propose a new paradigm which encodes image patch details by encoding the patch and subsequently using this sparse representation as input to a neural network to compare the patches. As sparse coding is based on a generative model of natural image patches, it can represent the patch in terms of the fundamental visual components from which it has been composed of, leading to similar sparse codes for patches which are built from similar components. Once the sparse coded features are extracted, we employ a fully-connected neural network, which captures the non-linear relationships between features, for comparison. We have evaluated our approach using the Liberty and Notredame subsets of the popular UBC patch dataset and set a new benchmark outperforming all state-of-the-art patch matching techniques for these datasets.