IPOLIPOLhttp://www.ipol.im/feed/IPOL Preprints — Latest public preprints from IPOL.ikiwiki2024-03-14T10:25:08ZDehazing with Dark Channel Prior: Analysis and Implementationhttp://www.ipol.im/pub/pre/530/Jose-Luis Lisani,
Charles Hessel2024-03-14T10:25:08Z2024-03-14T10:25:08Z
In outdoor scenes, atmospheric absortion and scattering attenuate the radiance received by the
camera and may produce haze. In 2009 He et al. proposed a simple but effective dehazing
algorithm based on a hypothesis called the 'dark channel prior' (DCP). Based on this prior
several other dehazing methods have been published in recent years. In this paper we review
the original algorithm by He et al., together with some posterior improvements proposed by the
same and other authors. We also analyze the effect of the parameters on the results and we
study a variant of the method proposed by Drews et al. for the analysis of haze in underwater
images.
A Closed Form Solution to Natural Image Mattinghttp://www.ipol.im/pub/pre/532/Mahdi Ranjbar,
Aissa Abdelaziz,
Mohammad Ali Jauhar2024-03-13T18:46:46Z2024-03-13T18:46:46Z
Natural image matting refers to the process of estimating the foreground opacity, also known
as the alpha matte, of an input image and extracting the foreground layer. It is a fundamental
and challenging task in computer vision and finds applications in various fields related to image
processing such as film and image editing, advertising, and medical diagnosis. Numerous
approaches have been proposed to address this challenge incorporating both traditional and deep
learning techniques. In this paper, we reproduce the paper "A Closed Form Solution to Natural
Image Matting", also referred to as "Closed Form Matting". The proposed algorithm is based
on local smoothness assumptions on foreground and background colors, the color-line model,
and provides a simple closed-form solution that requires sparse scribble constraints instead of
more cumbersome and hard-to-develop trimap constraints. We present extended derivations, a
Python-based implementation, an online demo, along with comparison on contemporary methods
and ablation study on the effects of hyper-parameters.
Non-local Matching of Superpixel-based Deep Features for Color transfer and Colorizationhttp://www.ipol.im/pub/pre/522/Roxane Leduc,
Hernan Castillo,
Nicolas Papadakis2024-01-17T18:11:57Z2024-01-17T16:13:41Z
In this article, we give a thorough description of the algorithm proposed in [H. Carrillo, M.
Clément and A. Bugeau, Non-local matching of superpixel-based deep features for color transfer,
2021] for color transfer by relying on a robust non-local correspondence between low-level features
at high resolution. An adaptation of this method to colorization process is also described.
We highlight the overall relevant results obtained with this technique for both applications and
also show its limitations.
Image Forgery Detection Based on Noise Inspection: Analysis and Refinement of the Noisesniffer Methodhttp://www.ipol.im/pub/pre/462/Marina Gardella,
Pablo Musé,
Miguel Colom,
Jean-Michel Morel2024-02-02T08:57:14Z2023-12-12T16:39:17Z
Images undergo a complex processing chain from the moment light reaches the camera's sensor until the final digital image is delivered. Each of its operations leaves traces on the noise model which enable forgery detection through noise analysis. In this article, we describe the Noisesniffer method [Gardella et al., IEEE International Workshop on Biometrics and Forensics, 2021]. This method estimates for each image a background stochastic model which makes it possible to detect local noise anomalies characterized by their number of false alarms. We improve on the original formulation of the method by introducing a region-growing algorithm to detect local deviations from the background model. Results show that the proposed method outperforms the previous version as well as the state of the art.
Experimental Improvements of Global Optimization Algorithms for Lipschitz Functionshttp://www.ipol.im/pub/pre/469/Perceval Beja-Battais,
Gaëtan Serré,
Sophia Chirrane2023-06-05T18:33:05Z2023-06-05T18:33:05Z
In this paper, we define an experimental context in which we tested the performances of LIPO and AdaLIPO, two global optimization algorithms for Lipschitz functions, introduced in [C. Malherbe and N. Vayatis, Global optimization of lipschitz functions, 2017]. We provide experimental proofs of the efficiency of
those algorithms, led numerical statistical analysis of our results, and suggested
two intuitive improvements from the vanilla version of the algorithms, referred
as LIPO-E and AdaLIPO-E. Within our test bench, these improvements allow
the algorithms to converge significantly faster and whenever they struggle to
find a better maximizer. Finally, we defined the scope of application of LIPO
and AdaLIPO. We show that they are very prone to the curse of dimensionality
and tend quickly to Pure Random Search when the dimension increases. We
provide source code for LIPO, AdaLIPO, and our enhanced versions
An implementation of 'Efficient Multi-Stage Video Denoising Method' and some variantshttp://www.ipol.im/pub/pre/464/Zhe Zheng,
Gabriele Facciolo,
Pablo Arias2023-03-14T12:42:14Z2023-02-28T18:44:12Z
Recently, the field of image and video denoising has undergone a revolution
thanks to deep learning approaches. These methods outperform traditional
model-based approaches in almost every image/video restoration problem. In this paper,
we propose an implementation of a recent approach proposed for video denoising,
namely Efficient Multi-stage Video Denoising method (EMVD). The method
has a lightweight and interpretable architecture consisting of three stages: temporal
fusion, denoising, and refinement stages. We reproduce this method and propose
three modifications aimed at improving its performance. (1) We apply motion
compensation to make better use of temporal redundancy, (2) we apply variance
stabilization to help this lightweight network deal with signal-dependent noise and
(3) we decouple occlusion detection and fusion weights prediction. We evaluate the
original method and the proposed modifications on a task of raw video denoising.
Thin-plate Splines on the Sphere for Interpolation, Computing Global Averages, and Solving Inverse Problemshttp://www.ipol.im/pub/pre/451/Max Dunitz2023-08-01T09:26:20Z2022-12-13T14:42:22Z
In many applications,
planar spline interpolations based on projections of the sphere onto a plane are unsatisfactory, and spherical splines are desired. Wahba (1981) defined the thin-plate splines on the sphere by analogy with the polynomial splines on the circle and the thin-plate splines in R^d. The thin-plate spline fit to a scattered data set on the sphere is the solution to an empirical risk minimization problem that penalizes the infidelity of the fit to the data and its 'wiggliness'. This latter term is the square of a seminorm based on the Laplace-Beltrami operator. The minimization problem is posed in a reproducing kernel Hilbert space (RKHS) of functions determined by this wiggliness penalty and to which corresponds an isotropic kernel, for which closed-form expressions (in terms of the polylogarithm) were found by Wendelberger (1982) and re-discovered by Beatson and zu Castell (2018). These closed-form expressions make not just spline interpolation but also downstream signal-processing tasks, such as cubature or solving inverse problems, more tractable in fields where scattered data and spherical models are common, such as remote sensing, geostatistics, oceanography, meteorology, motion planning, graphics, and medical imaging. In this paper, we present a tutorial on spline methods in RKHSs and show how they can be used to interpolate, smooth, and numerically integrate scattered data on the sphere and solve related inverse problems. The accompanying demo compares thin-plate spline interpolation over the sphere using these closed-form expressions for the kernel, thin-plate splines on an equirectangular projection, and natural cubic splines on a one-dimensional latitudinal projection used in greenhouse gas monitoring. Global mean values of the interpolation surfaces are presented as well, to illustrate how this isotropic spherical kernel - which penalizes wiggliness without concern for application-specific factors like atmospheric winds - affects the computation of global averages.
Fixed Pattern Noise Reduction: Temporal High Pass Filterhttp://www.ipol.im/pub/pre/436/Arnaud Barral2022-11-25T08:21:14Z2022-11-25T08:21:14Z
Temporal high pass filter methods are a family of methods for Fixed Pattern Noise (FPN) reduction. They are recursive real time methods that apply a high-pass temporal filter to remove the FPN. FPN is a temporally coherent noise present on video due to the non-uniformity response of the sensors. It is a common problem for infrared videos and can degrade the quality of the observation. In this work we will study and compare three classical temporal high pass filter FPNR methods.