We present an image dehazing algorithm that leverages zero-shot learning principles and layer disentanglement techniques, surpassing the performance of existing models. Our method uniquely operates on a single hazy image for both learning and inference, eliminating the need for extensive training datasets. The optimization process of the proposed architecture is guided by a classical physical scattering model and by information extracted from the input hazy image itself. This approach ensures that the dehazed output maintains color fidelity and remains artifact-free. Such quality preservation is particularly noteworthy, as other learning-based methods often struggle with color distortions and artifacts when applied to real-world hazy images due to the domain-shift problem.

The authors present a method for the enhancement of backlit images, i.e. images in which the main source of light is behind the photography subject. These images contain, simultaneously, very dark and very bright regions. In this situation, a single tone mapping function is unable to enhance the whole image. They propose the use of several such tone mappings, some of them enhancing the dark regions while others enhancing the bright regions, and then the combination of all these results using an image fusion algorithm. Qualitative and quantitative results confirm the validity of the proposed method.

A new method for denoising video sequences is presented. The method is able to deal with poor quality sequences affected by both noise and compression, as for example mobile phone videos recorded in low-light conditions. In this real scenario, the usual white Gaussian uniform noise assumption fails, and the state-of-the art denoising algorithms are ineffective. The proposed method first estimates a signal dependent noise model at each level of a multi-scale pyramid; then, a variance stabilization transform is applied at each scale; and, finally, a denoising algorithm is applied on the stabilized image sequence. This algorithm takes advantage of self similarity and redundancy of adjacent frames and uses motion compensation by regularized optical flow methods, which permits robust patch comparison in a spatio-temporal volume. The experiments illustrate that the proposed method is able to correctly remove highly correlated noise from real dark and compressed movie sequences. Finally, in order to assess numerically the performance of the proposed algorithm, we introduce a new database of noisy and compressed image sequences with known ground truth. The numerical comparisons with the introduced database corroborate the superior performance of the method.

A new local image enhancement technique is proposed. It is based on a logarithmic mapping function that is adapted to the luminance characteristics of the neighborhood of each pixel. The method permits to simultaneously increase the luminance in dark regions and decrease it in bright regions. The result is an image with an overall improved contrast.

We propose a new video denoising algorithm combining state of the art image and video denoising algorithms. We extend the DDID [1] algorithm to video sequences and then combine it with the SPTWO [2] method. The experimentation illustrates how the new method keeps the best of each algorithm, being superior both visually and numerically to other state of the art techniques.

The a contrario framework is a statistical formulation of a perception principle that permits one to detect meaningful structures in data. It has been applied to the detection of lines and contours in images, moving objects in video, etc., but no attempt has been made to use it for the detection of faces. The goal of this paper is to show that the a contrario formulation can be adapted to the face detection method described by Viola and Jones in their seminal work. We propose an alternative to the cascade of classifiers proposed by the authors by introducing a stochastic a contrario model for the detections of a single classifier, from which adaptive detection thresholds may be inferred. The result is a single classifier whose detection rates are similar to those of a cascade of classifiers. Moreover, we show how a very short cascade of classifiers can be constructed, which improves the accuracy of a classical cascade, at a much lower computational cost. The results prove the validity of the a contrario approach for face detection and suggest that the same principles might be used to improve the performance of state-of-the-art methods.

In areas of ecological interest, the detection and control of seaweed such as Posidonia Oceanica is usually performed by divers. Due to the limited capacity of the scuba tanks and the human security protocols, this task involves several short immersions leading to poor temporal and spatial data resolution. Thus, it is desirable to automate this task by means of underwater robots. This paper describes a method to autonomously detect Posidonia Oceanica in the imagery gathered by an underwater robot. The proposed approach uses a set of Gabor filters to characterize an image. This characterization is used to detect the regions containing seaweed by means of a Support Vector Machine. The experiments, conducted with an Autonomous Underwater Robot in several marine areas of Mallorca, show promising results towards the automated seafloor classification from extended video sequences.

Enhancement algorithms are absolutely necessary for the visualization of both shadowed and bright image regions. Defining algorithms that permit to visualize them simultaneously without altering the image content is therefore extremely relevant for remote sensing applications. In this paper, we present the results of two successive benchmarks which tested the performance of the state-of-the-art contrast enhancement and tone-mapping algorithms applied to satellite images. Experts from the French Space Agency Centre National d'Etudes Spatiales (CNES), Service Régional de Traitement d'Image et de Télédétection (SERTIT), and two European universities assessed the quality and fidelity of the results of several state-of-the-art enhancement algorithms on the excerpts from seven images (five Pleiades and two simulated 30-cm images). The first benchmark permitted to tighten the procedure and the selection of the test images for the second one, and to make a first selection of concurrent algorithms. The second benchmark not only included the best algorithms selected by the first benchmark but also added even more competitors in the tone-mapping class. The results of both benchmarks were coherent. They point a particular retinex-based algorithm as the best compromise between the competitive requirements of a contrast enhancement in dark regions and a preservation of detail in bright parts.

A novel image sequence denoising algorithm is presented. The proposed approach takes advantage of the self-similarity and redundancy of adjacent frames. The algorithm is inspired by fusion algorithms, and as the number of frames increases, it tends to a pure temporal average. The use of motion compensation by regularized optical flow methods permits robust patch comparison in a spatiotemporal volume. The use of principal component analysis ensures the correct preservation of fine texture and details. An extensive comparison with the state-of-the-art methods illustrates the superior performance of the proposed approach, with improved texture and detail reconstruction.

We present a new method to automatically detect, track, sort, search, display and record meaningful changes in a video sequence. The meaningfulness of changes is measured in terms of their False Alarm Rate, which is controlled by the user. The process entails four main steps: a) background extraction; b) change detection; c) change tracking and recording; and d) classification of change according to its attributes (size, color, etc.). The information obtained from the classification step shall be used to index the video data.

In this work, we propose a method to segment a 1-D histogram without a priori assumptions about the underlying density function. Our approach considers a rigorous definition of an admissible segmentation, avoiding over and under segmentation problems. A fast algorithm leading to such a segmentation is proposed. The approach is tested both with synthetic and real data. An application to the segmentation of written documents is also presented. We shall see that this application requires the detection of very small histogram modes, which can be accurately detected with the proposed method.

This paper presents a software-based parameter-free method for the demultiplexing of a video stream (L. Rudin et al., 2004) that is missing camera labeling information. The method is based on the observation that frames coming from the same input camera share some common characteristic features. These features are extracted from the input frames and grouped together according to statistical criteria. As a result of this grouping the number of different input sources in the video stream is inferred and it is possible to ascertain the source for each frame.

Color palettes are an important tool for color image analysis, since they are the initial point of different techniques such as quantization or indexing. This paper presents a new method for the automatic construction of a color palette, which adjusts dynamically its number of colors according to the visual content of the image. The method is based on appropriately segmenting the HSI color space, which is achieved by individually partitioning the histograms associated to each color component. As a result we obtain a hierarchical color palette, which represents the color image with a reduced number of colors.

In this paper the problem of detecting changes between two photographs of the same scene taken at different dates is addressed. Considering that both images are already accurately registered our problem reduces to a) detect changes between corresponding pixels, and b) determine whether these changes are a clue of a major change in the scene. The solution of a) involves the use of spectral invariant features, since we consider the general situation of comparing photographs coming from different spectral channels. The answer to b) implies the computation of an absolute threshold above which a region of the image will be detected as having "meaningful changes". In order to do that, we apply a recently introduced method yielding accurate false alarm rates for each detection. We show that this method permits to help significantly photo-interprets in their search for major changes in a scene. This will be illustrated by a striking application, the detection of the explosion of the AZF chemical plant in Toulouse (France) in September 2001.

A novel approach for shape preserving contrast enhancement is presented in this paper. Contrast enhancement is achieved by means of a local histogram equalization algorithm which preserves the level-sets of the image. This basic property is violated by common local schemes, thereby introducing spurious objects and modifying the image information. The scheme is based on equalizing the histogram in all the connected components of the image, which are defined based both on the grey-values and spatial relations between pixels in the image, and following mathematical morphology, constitute the basic objects in the scene. We give examples for both grey-value and color images.

A novel approach for shape preserving contrast enhancement is presented. Contrast enhancement is achieved by means of a local histogram equalization algorithm which preserves the level-sets of the image. This basic property is violated by common local schemes, thereby introducing spurious objects and modifying the image information. The scheme is based on equalizing the histogram in all the connected components of the image, which are defined based on the image grey-values and spatial relations between its pixels. Following mathematical morphology, these constitute the basic objects in the scene. We give examples for both grey-valued and color images.