We motivate a new line of image forensics, and propose a novel approach to photographer identification, a rarely explored authorship attribution problem. A preliminary proof-of-concept study shows the feasibility of our method. Our contribution is a forensic method for photographer de-anonymisation, and the method also imposes a novel privacy threat.

This paper considers the problem of sampling and reconstruction of a continuous-time sparse signal without assuming the knowledge of the sampling instants or the sampling rate. This topic has its roots in the problem of recovering multiple echoes of light from its low-pass filtered and auto-correlated, time-domain measurements. Our work is closely related to the topic of sparse phase retrieval and in this context, we discuss the advantage of phase-free measurements. While this problem is ill-posed, cues based on physical constraints allow for its appropriate regularization. We validate our theory with experiments based on customized, optical time-of-flight imaging sensors. What singles out our approach is that our sensing method allows for temporal phase retrieval as opposed to the usual case of spatial phase retrieval. Preliminary experiments and results demonstrate a compelling capability of our phaseretrieval based imaging device.

When multiple light paths combine at a given location on an image sensor, an image mixture is created. Demixing or recovering the original constituent components in such cases is a highly ill-posed problem. A number of elegant solutions have thus been developed in the literature, relying on measurement diversity such as polarization, shift, motion, or scene features. In this paper, we approach the image-mixing problem as a time-resolved phenomenon-if every photon arriving at the sensor could be time-stamped, the demixing problem would then amount to separating transient events in time. Based on this idea, we first show that, while acquiring measurements is prohibitive and challenging in the time domain, this task is surprisingly straightforward in the frequency domain. We then establish a link between frequency-domain measurements and consumer time-of-flight (ToF) imaging. Finally, we propose a demixing algorithm, relying only on magnitude information of the ToF sensor. We show that our problem is closely tied to the topic of phase retrieval and that for K-image mixture, (K2-K)/2+1 magnitude-only ToF measurements suffice to demix images exactly in noiseless settings. Our developments are corroborated with experiments on synthetic and ToF data acquired using the Microsoft Kinect sensor.

We introduce an adaptive continuous-domain modeling approach to texture and natural images. The continuous-domain image is assumed to be a smooth function, and we embed it in a parameterized Sobolev space. We point out a link between Sobolev spaces and stochastic auto-regressive models, and exploit it for optimally choosing Sobolev parameters from available pixel values. To this aim, we use exact continuous-to-discrete mapping of the auto-regressive model that is based on symmetric exponential splines. The mapping is computationally efficient, and we exploit it for maximizing an approximated Gaussian likelihood function.We account for non-Gaussian Lévy-type processes by deriving a more robust estimator that is based on the sample auto-correlation sequence. Both estimators use multiple initialization values for overcoming the local minima structure of the fitting criteria. Experimental image resizing results indicate that the auto-correlation criterion can cope better with non-Gaussian processes and model mismatch. Our work demonstrates the importance of the auto-correlation function in adaptive image interpolation and image modeling tasks, and we believe it is instrumental in other image processing tasks as well.

In this paper, we reconstruct signals from underdetermined linear measurements where the componentwise gains of the measurement system are unknown a priori. The reconstruction is performed through an adaptation of the messagepassing algorithm called adaptive GAMP that enables joint gain calibration and signal estimation. To evaluate our approach, we apply it to the problem of sparse recovery and compare it against an ℓ1-based approach. We numerically show that adaptive GAMP yields excellent results even for a moderate amount of data. It approaches the performance of oracle GAMP where the gains are perfectly known asymptotically.

Practical image-acquisition systems are often modeled as a continuous-domain prefilter followed by an ideal sampler, where generalized samples are obtained after convolution with the impulse response of the device. In this paper, our goal is to interpolate images from a given subset of such samples. We express our solution in the continuous domain, considering consistent resampling as a data-fidelity constraint. To make the problem well posed and ensure edge-preserving solutions, we develop an efficient anisotropic regularization approach that is based on an improved version of the edge-enhancing anisotropic diffusion equation. Following variational principles, our reconstruction algorithm minimizes successive quadratic cost functionals. To ensure fast convergence, we solve the corresponding sequence of linear problems by using multigrid iterations that are specifically tailored to their sparse structure. We conduct illustrative experiments and discuss the potential of our approach both in terms of algorithmic design and reconstruction quality. In particular, we present results that use as little as 2% of the image samples.

Compressed sensing can substantially reduce the number of samples required for conventional signal acquisition at the expense of an additional reconstruction procedure. It also provides robust reconstruction when using quantized measurements, including in the one-bit setting. In this paper, our goal is to design a framework for binary compressed sensing that is adapted to images. Accordingly, we propose an acquisition and reconstruction approach that complies with the high dimensionality of image data and that provides reconstructions of satisfactory visual quality. Our forward model describes data acquisition and follows physical principles. It entails a series of random convolutions performed optically followed by sampling and binary thresholding. The binary samples that are obtained can be either measured or ignored according to predefined functions. Based on these measurements, we then express our reconstruction problem as the minimization of a compound convex cost that enforces the consistency of the solution with the available binary data under total-variation regularization. Finally, we derive an efficient reconstruction algorithm relying on convex-optimization principles. We conduct several experiments on standard images and demonstrate the practical interest of our approach.

We introduce a new method for adaptive one-bit quantization of linear measurements and propose an algorithm for the recovery of signals based on generalized approximate message passing (GAMP). Our method exploits the prior statistical information on the signal for estimating the minimum-mean-squared error solution from one-bit measurements. Our approach allows the one-bit quantizer to use thresholds on the real line. Given the previous measurements, each new threshold is selected so as to partition the consistent region along its centroid computed by GAMP. We demonstrate that the proposed adaptive-quantization scheme with GAMP reconstruction greatly improves the performance of signal and image recovery from one-bit measurements.

We present nonquadratic Hessian-based regularization methods that can be effectively used for image restoration problems in a variational framework. Motivated by the great success of the total-variation (TV) functional, we extend it to also include second-order differential operators. Specifically, we derive second-order regularizers that involve matrix norms of the Hessian operator. The definition of these functionals is based on an alternative interpretation of TV that relies on mixed norms of directional derivatives. We show that the resulting regularizers retain some of the most favorable properties of TV, i.e., convexity, homogeneity, rotation, and translation invariance, while dealing effectively with the staircase effect. We further develop an efficient minimization scheme for the corresponding objective functions. The proposed algorithm is of the iteratively reweighted least-square type and results from a majorization-minimization approach. It relies on a problem-specific preconditioned conjugate gradient method, which makes the overall minimization scheme very attractive since it can be applied effectively to large images in a reasonable computational time. We validate the overall proposed regularization framework through deblurring experiments under additive Gaussian noise on standard and biomedical images.

We suggest a continuous-domain stochastic modeling of images that is invariant to spatial resolution. Specifically, we are proposing an estimator that is calibrated with respect to the sampling step, and that can potentially handle aliased data. Motivated by Markov random fields, we assume a continuous-domain ARMA model and suggest an algorithm for estimating the continuous-domain parameters from the sampled data. The continuous-domain parameters we estimate provide features that can further be used for image classification, segmentation and interpolation, regardless of sampling interval values and of aliasing effects that may appear in the digital image. Experimental results indicate that the proposed approach is preferable over a discrete-domain ARMA modeling.

In this paper, we propose a novel second-order regularizer based on the maximum response of the second-order directional derivative, assuming that the image under consideration belongs to the class of piecewise-linear signals. Compared to total-variation regularization that preserves edges but transforms piecewise-smooth regions into piecewise-constant regions, the proposed model is able to restore piecewise-linear regions and finer details. Deconvolution experiments demonstrate the performance of our approach in terms of the quality of reconstruction.

Because more output data must be created than is available from the input, magnification is an ill-posed problem. Traditional magnification relies on resampling an interpolation model at the appropriate rate; unfortunately, this simple solution is blind to the presence of the analog filter that was implicitly present when the samples of the function to be magnified were acquired. Consistent resampling has been introduced to take this into account, but it turns out that this solution is still under-constrained. In this paper, we propose regularization as a way to devise a deterministic magnification method that fully satisfies consistency constraints in the absence of noise, and at the same time that produces an output that best fulfills a wide class of criteria for regularity. Contrarily to many other methods, ours has been designed without ever leaving the continuous domain. We conduct experiments that show the benefit of our approach.