Abstract Film grain refers to the specific texture of film‐acquired images, due to the physical nature of photographic film. Being a visual signature of such images, there is a strong interest in the film‐industry for the rendering of these textures for digital images. Some previous works are able to closely mimic the physics of films and produce high quality results, but are computationally expensive. We propose a method based on a lightweight neural network and a texture aware loss function, achieving realistic results with very low complexity, even for large grains and high resolutions. We evaluate our algorithm both quantitatively and qualitatively with respect to previous work.

Learning disentangled representations for time series is a promising path to facilitate reliable generalization to in- and out-of distribution (OOD), offering benefits like feature derivation and improved interpretability and fairness, thereby enhancing downstream tasks. We focus on disentangled representation learning for home appliance electricity usage, enabling users to understand and optimize their consumption for a reduced carbon footprint. Our approach frames the problem as disentangling each attribute's role in total consumption. Unlike existing methods assuming attribute independence which leads to non-identiability, we acknowledge real-world time series attribute correlations, learned up to a smooth bijection using contrastive learning and a single autoencoder. To address this, we propose a Disentanglement under Independence-Of-Support via Contrastive Learning (DIOSC), facilitating representation generalization across diverse correlated scenarios. Our method utilizes innovative \textit{l}-variational inference layers with self-attention, effectively addressing temporal dependencies across bottom-up and top-down networks. We find that DIOSC can enhance the task of representation of time series electricity consumption. We introduce TDS (Time Disentangling Score) to gauge disentanglement quality. TDS reliably reflects disentanglement performance, making it a valuable metric for evaluating time series representations disentanglement. Code available at https://institut-polytechnique-de-paris.github.io/time-disentanglement-lib.

Deep learning methods for image restoration have produced impressive results over recent years. Nevertheless, they generalize poorly and need large learning image datasets to be collected for each new acquisition modality. In order to avoid the building of such datasets, it has been recently proposed to develop synthetic image datasets for training image restoration methods, using scale invariant dead leaves models. While the geometry of such models can be successfully encoded with only a few parameters, the color content cannot be straightforwardly encoded. In this paper, we leverage the concept of color lines prior to build a light parametric color model relying on a chromaticity/luminance factorization. Further, we show that the corresponding synthetic dataset can be used to train neural networks for the denoising of RAW images from different camera-phones, without using any image from these devices. This shows the potential of our approach to increase the generalization capacity of learning-based denoising approaches in real case scenarios.

Speckle reduction is a necessary step for many applications. Very effective methods have been developed in the recent years for single-image speckle reduction and multi-temporal speckle filtering. However, to reduce the presence of sidelobes around bright targets, SAR images are spectrally weighted and this processing impacts the speckle statistics by introducing spatial correlations. These correlations severely impact speckle reduction methods that require uncorrelated speckle as input. Thus, spatial down-sampling is typically applied to reduce the speckle spatial correlations prior to speckle filtering. To better preserve the spatial resolution, we describe how to correctly resample SAR images and extract bright targets in order to process full-resolution images with speckle-reduction methods.

In order to overcome the limited depth of field of usual photographic devices, a common approach is multi-focus image fusion (MFIF). From a stack of images acquired with different focus settings, these methods aim at fusing the content of the images of the stack to produce a final image that is sharp everywhere. Such methods can be very efficient, but when a global geometric alignment of images is out-of-reach, or when some objects are moving, the final image shows ghosts or other artefacts. In this paper, we propose a generic method to overcome these limitations. We first select a reference image, and then, for each image of the stack, reconstruct an image that shares the geometry of the reference and the sharpness content of the image at hand. The reconstruction is achieved thanks to a specially crafted modification of the PatchMatch algorithm, adapted to blurred images, and to a dedicated postprocessing for correcting reconstruction errors. Then, from the new image stack, MFIF is performed to produce a sharp result. We show the efficiency of the result on a database of challenging cases of hand-held shots containing moving objects.

The aim of this work is to present a resampling scheme for SAR images that preserves spatial resolution and produces statistically accurate images at the same time. Indeed, SAR images are, for reasons due to their acquisition process, well sampled signals according to the Shannon sampling theory. In the presence of strong responses, that we will refer to as targets, a sinc-like function centered at the target is smeared over the entire image and is particularly visible in the range of tens of pixels surrounding the target. To mitigate this phenomenon, the usual solution is to apply an apodization window in the Fourier domain so as to change the cardinal sine impulse response into a much rapidly decaying one. This approach has two major drawbacks. It reduces the resolution of the image and introduces inaccurate statistical dependency between pixels. We propose to resample the image in an adaptive and robust way so that the target smear is canceled and the new sampled image is completely faithful to the underlying signal.

Images acquired by the Moderate Resolution Imaging Spectroradiometer (MODIS) aboard Terra and Aqua exhibit strong detector striping. This artifact is common to most pushbroom scanners and affects both visual interpretation and radiometric integrity of remotely sensed data. A considerable effort has been made to remove stripe noise and reduce its impact on high-level products. Despite the variety of destriping algorithms proposed in the literature, complete removal of stripes without signal distortion is yet to be overcome. In this paper, we tackle the striping issue from a variational angle. Basic statistical assumptions used in previous techniques are replaced by a much realistic geometrical consideration on the striping unidirectional variations. The resulting algorithm is tested on Aqua and Terra MODIS data contaminated with severe stripes and is shown to provide optimal qualitative and quantitative results.

The Moderate Resolution Imaging Spectrometer (MODIS) monitors the earth in 36 spectral bands using a cross-track double-sided continuously rotating scan mirror. The imperfect calibration of the linear arrays of detectors and additional random noise in the internal calibration system induce detector-to-detector stripes, mirror side stripes and noisy stripes visible in most emissive bands. This artefact affects seriously the visual quality and radiometric integrity of measured data. Several approaches including Fourier filtering, wavelet analysis and statistical techniques such as moment matching or histogram matching have been used to reduce striping on MODIS Data. Despite an extensive and diverse destriping literature, most techniques display residual stripes if not strong distortion from the original image. In this paper, we introduce a robust destriping methodology based on a variational approach.

Space agencies are rapidly building up massive image databases. A particularity of these databases is that they are made of images with different, but known, resolutions. In this paper, we introduce a new scheme allowing us to compare and index images with different resolutions. This scheme relies on a simplified acquisition model of satellite images and uses continuous wavelet decompositions. We establish a correspondence between scales which permits us to compare wavelet decompositions of images having different resolutions. We validate the approach through several matching and classification experiments, and we show that taking the acquisition process into account yields better results than just using scaling properties of wavelet features.

We study the problem of finding the characteristic scale of a given satellite image. This feature is defined so that it does not depend on the spatial resolution of the image. This is a different problem than achieving scale invariance, as often studied in the literature. Our approach is based on the use of a linear scale space and the total variation (TV). The critical scale is defined as the one at which the normalized TV reaches its maximum. It is shown experimentally, both on synthetic and real data, that the computed characteristic scale is resolution independent.

We study the problem of finding the characteristic scale of a given satellite image. We want to define this feature so that it does not depend on the spatial resolution of the image. Our approach is based on the use of a linear scale space and the total variation. The critical scale is defined as the one at which the normalized total variation is maximum.

In this paper, we propose a new scheme to extrapolate wavelet features with respect to the resolution. By explicitly taking into account the acquisition process of satellite images, we compute how wavelet features behave when the resolution changes. This approach is validated by classifying satellite images with different resolutions.

We address the problem of computing a local orientation map in a digital image. We show that standard image gray level quantization causes a strong bias in the repartition of orientations, hindering any accurate geometric analysis of the image. In continuation, a simple dequantization algorithm is proposed, which maintains all of the image information and transforms the quantization noise in a nearby Gaussian white noise (we actually prove that only Gaussian noise can maintain isotropy of orientations). Mathematical arguments are used to show that this results in the restoration of a high quality image isotropy. In contrast with other classical methods, it turns out that this property can be obtained without smoothing the image or increasing the signal-to-noise ratio (SNR). As an application, it is shown in the experimental section that, thanks to this dequantization of orientations, such geometric algorithms as the detection of nonlocal alignments can be performed efficiently. We also point out similar improvements of orientation quality when our dequantization method is applied to aliased images.