Coloma Ballester

Alejandro Cartas, Coloma Ballester, Gloria Haro

Action spotting in soccer videos is the task of identifying the specific time when a certain key action of the game occurs. Lately, it has received a large amount of attention and powerful methods have been introduced. Action spotting involves understanding the dynamics of the game, the complexity of events, and the variation of video sequences. Most approaches have focused on the latter, given that their models exploit the global visual features of the sequences. In this work, we focus on the former by (a) identifying and representing the players, referees, and goalkeepers as nodes in a graph, and by (b) modeling their temporal interactions as sequences of graphs. For the player identification, or player classification task, we obtain an accuracy of 97.72% in our annotated benchmark. For the action spotting task, our method obtains an overall performance of 57.83% average-mAP by combining it with other audiovisual modalities. This performance surpasses similar graph-based methods and has competitive results with heavy computing methods. Code and data are available at https://github.com/IPCV/soccer_action_spotting.

Coloma Ballester, Aurélie Bugeau, Hernan Carrillo et al.

Colorization is a process that converts a grayscale image into a color one that looks as natural as possible. Over the years this task has received a lot of attention. Existing colorization methods rely on different color spaces: RGB, YUV, Lab, etc. In this chapter, we aim to study their influence on the results obtained by training a deep neural network, to answer the question: "Is it crucial to correctly choose the right color space in deep-learning based colorization?". First, we briefly summarize the literature and, in particular, deep learning-based methods. We then compare the results obtained with the same deep neural network architecture with RGB, YUV and Lab color spaces. Qualitative and quantitative analysis do not conclude similarly on which color space is better. We then show the importance of carefully designing the architecture and evaluation protocols depending on the types of images that are being processed and their specificities: strong/small contours, few/many objects, recent/archive images.

Coloma Ballester, Aurélie Bugeau, Hernan Carrillo et al.

Image colorization aims to add color information to a grayscale image in a realistic way. Recent methods mostly rely on deep learning strategies. While learning to automatically colorize an image, one can define well-suited objective functions related to the desired color output. Some of them are based on a specific type of error between the predicted image and ground truth one, while other losses rely on the comparison of perceptual properties. But, is the choice of the objective function that crucial, i.e., does it play an important role in the results? In this chapter, we aim to answer this question by analyzing the impact of the loss function on the estimated colorization results. To that goal, we review the different losses and evaluation metrics that are used in the literature. We then train a baseline network with several of the reviewed objective functions: classic L1 and L2 losses, as well as more complex combinations such as Wasserstein GAN and VGG-based LPIPS loss. Quantitative results show that the models trained with VGG-based LPIPS provide overall slightly better results for most evaluation metrics. Qualitative results exhibit more vivid colors when with Wasserstein GAN plus the L2 loss or again with the VGG-based LPIPS. Finally, the convenience of quantitative user studies is also discussed to overcome the difficulty of properly assessing on colorized images, notably for the case of old archive photographs where no ground truth is available.

Marcelo Sanchez, Gil Triginer, Coloma Ballester et al.

Editing and retouching facial attributes is a complex task that usually requires human artists to obtain photo-realistic results. Its applications are numerous and can be found in several contexts such as cosmetics or digital media retouching, to name a few. Recently, advancements in conditional generative modeling have shown astonishing results at modifying facial attributes in a realistic manner. However, current methods are still prone to artifacts, and focus on modifying global attributes like age and gender, or local mid-sized attributes like glasses or moustaches. In this work, we revisit a two-stage approach for retouching facial wrinkles and obtain results with unprecedented realism. First, a state of the art wrinkle segmentation network is used to detect the wrinkles within the facial region. Then, an inpainting module is used to remove the detected wrinkles, filling them in with a texture that is statistically consistent with the surrounding skin. To achieve this, we introduce a novel loss term that reuses the wrinkle segmentation network to penalize those regions that still contain wrinkles after the inpainting. We evaluate our method qualitatively and quantitatively, showing state of the art results for the task of wrinkle removal. Moreover, we introduce the first high-resolution dataset, named FFHQ-Wrinkles, to evaluate wrinkle detection methods.

Coloma Ballester, Aurelie Bugeau, Samuel Hurault et al.

Image inpainting refers to the restoration of an image with missing regions in a way that is not detectable by the observer. The inpainting regions can be of any size and shape. This is an ill-posed inverse problem that does not have a unique solution. In this work, we focus on learning-based image completion methods for multiple and diverse inpainting which goal is to provide a set of distinct solutions for a given damaged image. These methods capitalize on the probabilistic nature of certain generative models to sample various solutions that coherently restore the missing content. Along the chapter, we will analyze the underlying theory and analyze the recent proposals for multiple inpainting. To investigate the pros and cons of each method, we present quantitative and qualitative comparisons, on common datasets, regarding both the quality and the diversity of the set of inpainted solutions. Our analysis allows us to identify the most successful generative strategies in both inpainting quality and inpainting diversity. This task is closely related to the learning of an accurate probability distribution of images. Depending on the dataset in use, the challenges that entail the training of such a model will be discussed through the analysis.

Pritam Mishra, Coloma Ballester, Dimosthenis Karatzas

The rapid growth of video content across domains such as surveillance, education, and social media has made efficient content understanding increasingly critical. Video summarization addresses this challenge by generating concise yet semantically meaningful representations, but existing approaches often rely on expensive manual annotations, struggle to generalize across domains, and incur significant computational costs due to complex architectures. Moreover, unsupervised and weakly supervised methods typically underperform compared to supervised counterparts in capturing long-range temporal dependencies and semantic structure. In this work, we propose TRIMMER (Temporal Relative Information Maximization for Multi-objective Efficient Reinforcement), a novel self-supervised reinforcement learning framework for video summarization. TRIMMER operates in two stages: it first learns robust representations via self-supervised learning and then performs spatio-temporal decision making through reinforcement learning guided by information-theoretic reward functions. Unlike prior approaches that rely on similarity-based objectives, our method introduces entropy-based metrics to capture higher-order temporal dynamics and semantic diversity, while computing rewards directly over selected frame indices to improve computational efficiency. Extensive experiments on standard benchmarks demonstrate that TRIMMER achieves state-of-the-art performance among unsupervised and self-supervised methods, while remaining competitive with leading supervised approaches, highlighting its effectiveness for scalable and generalizable video summarization.

Artur Díaz-Juan, Coloma Ballester, Gloria Haro

Video summarization aims to extract key shots from longer videos to produce concise and informative summaries. One of its most common applications is in sports, where highlight reels capture the most important moments of a game, along with notable reactions and specific contextual events. Automatic summary generation can support video editors in the sports media industry by reducing the time and effort required to identify key segments. However, the lack of publicly available datasets poses a challenge in developing robust models for sports highlight generation. In this paper, we address this gap by introducing a curated dataset for soccer video summarization, designed to serve as a benchmark for the task. The dataset includes shot boundaries for 237 matches from the Spanish, French, and Italian leagues, using broadcast footage sourced from the SoccerNet dataset. Alongside the dataset, we propose a baseline model specifically designed for this task, which achieves an F1 score of 0.3956 in the test set. Furthermore, we propose a new metric constrained by the length of each target summary, enabling a more objective evaluation of the generated content. The dataset and code are available at https://ipcv.github.io/SoccerHigh/.

Pritam Mishra, Coloma Ballester, Dimosthenis Karatzas

The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vital research area. However, many state-of-the-art methods depend heavily either on supervised annotations or on attention-based models, which are computationally expensive and brittle in the face of distribution shifts that hinder cross-domain applicability across datasets. We introduce a pioneering self-supervised video summarization model that captures both spatial and temporal dependencies without the overhead of attention, RNNs, or transformers. Our framework integrates a novel set of Markov process-driven loss metrics and a two-stage self supervised learning paradigm that ensures both performance and efficiency. Our approach achieves state-of-the-art performance on the SUMME and TVSUM datasets, outperforming all existing unsupervised methods. It also rivals the best supervised models, demonstrating the potential for efficient, annotation-free architectures. This paves the way for more generalizable video summarization techniques and challenges the prevailing reliance on complex architectures.

Marcelo Sanchez, Gil Triginer, Ignacio Sarasua et al.

Existing image inpainting methods have shown impressive completion results for low-resolution images. However, most of these algorithms fail at high resolutions and require powerful hardware, limiting their deployment on edge devices. Motivated by this, we propose the first baseline for REal-Time High-resolution image INpainting on Edge Devices (RETHINED) that is able to inpaint at ultra-high-resolution and can run in real-time ($\leq$ 30ms) in a wide variety of mobile devices. A simple, yet effective novel method formed by a lightweight Convolutional Neural Network (CNN) to recover structure, followed by a resolution-agnostic patch replacement mechanism to provide detailed texture. Specially our pipeline leverages the structural capacity of CNN and the high-level detail of patch-based methods, which is a key component for high-resolution image inpainting. To demonstrate the real application of our method, we conduct an extensive analysis on various mobile-friendly devices and demonstrate similar inpainting performance while being $\mathrm{100 \times faster}$ than existing state-of-the-art methods. Furthemore, we realease DF8K-Inpainting, the first free-form mask UHD inpainting dataset.

Adam Phillips, Daniel Grandes Rodriguez, Miriam Sánchez-Manzano et al.

In cinema, visual motifs are recurrent iconographic compositions that carry artistic or aesthetic significance. Their use throughout the history of visual arts and media is interesting to researchers and filmmakers alike. Our goal in this work is to recognise and classify these motifs by proposing a new machine learning model that uses a custom dataset to that end. We show how features extracted from a CLIP model can be leveraged by using a shallow network and an appropriate loss to classify images into 20 different motifs, with surprisingly good results: an $F_1$-score of 0.91 on our test set. We also present several ablation studies justifying the input features, architecture and hyperparameters used.

Adrià Arbués-Sangüesa, Adrián Martín, Paulino Granero et al.

Orientation is a crucial skill for football players that becomes a differential factor in a large set of events, especially the ones involving passes. However, existing orientation estimation methods, which are based on computer-vision techniques, still have a lot of room for improvement. To the best of our knowledge, this article presents the first deep learning model for estimating orientation directly from video footage. By approaching this challenge as a classification problem where classes correspond to orientation bins, and by introducing a cyclic loss function, a well-known convolutional network is refined to provide player orientation data. The model is trained by using ground-truth orientation data obtained from wearable EPTS devices, which are individually compensated with respect to the perceived orientation in the current frame. The obtained results outperform previous methods; in particular, the absolute median error is less than 12 degrees per player. An ablation study is included in order to show the potential generalization to any kind of football video footage.

Patricia Vitoria, Coloma Ballester

Flare spot is one type of flare artifact caused by a number of conditions, frequently provoked by one or more high-luminance sources within or close to the camera field of view. When light rays coming from a high-luminance source reach the front element of a camera, it can produce intra-reflections within camera elements that emerge at the film plane forming non-image information or flare on the captured image. Even though preventive mechanisms are used, artifacts can appear. In this paper, we propose a robust computational method to automatically detect and remove flare spot artifacts. Our contribution is threefold: firstly, we propose a characterization which is based on intrinsic properties that a flare spot is likely to satisfy; secondly, we define a new confidence measure able to select flare spots among the candidates; and, finally, a method to accurately determine the flare region is given. Then, the detected artifacts are removed by using exemplar-based inpainting. We show that our algorithm achieve top-tier quantitative and qualitative performance.

Samuel Hurault, Coloma Ballester, Gloria Haro

In a soccer game, the information provided by detecting and tracking brings crucial clues to further analyze and understand some tactical aspects of the game, including individual and team actions. State-of-the-art tracking algorithms achieve impressive results in scenarios on which they have been trained for, but they fail in challenging ones such as soccer games. This is frequently due to the player small relative size and the similar appearance among players of the same team. Although a straightforward solution would be to retrain these models by using a more specific dataset, the lack of such publicly available annotated datasets entails searching for other effective solutions. In this work, we propose a self-supervised pipeline which is able to detect and track low-resolution soccer players under different recording conditions without any need of ground-truth data. Extensive quantitative and qualitative experimental results are presented evaluating its performance. We also present a comparison to several state-of-the-art methods showing that both the proposed detector and the proposed tracker achieve top-tier results, in particular in the presence of small players.

Adrià Arbués-Sangüesa, Adrián Martín, Javier Fernández et al.

Given a monocular video of a soccer match, this paper presents a computational model to estimate the most feasible pass at any given time. The method leverages offensive player's orientation (plus their location) and opponents' spatial configuration to compute the feasibility of pass events within players of the same team. Orientation data is gathered from body pose estimations that are properly projected onto the 2D game field; moreover, a geometrical solution is provided, through the definition of a feasibility measure, to determine which players are better oriented towards each other. Once analyzed more than 6000 pass events, results show that, by including orientation as a feasibility measure, a robust computational model can be built, reaching more than 0.7 Top-3 accuracy. Finally, the combination of the orientation feasibility measure with the recently introduced Expected Possession Value metric is studied; promising results are obtained, thus showing that existing models can be refined by using orientation as a key feature. These models could help both coaches and analysts to have a better understanding of the game and to improve the players' decision-making process.

Adrià Arbués-Sangüesa, Adrián Martín, Javier Fernández et al.

Although orientation has proven to be a key skill of soccer players in order to succeed in a broad spectrum of plays, body orientation is a yet-little-explored area in sports analytics' research. Despite being an inherently ambiguous concept, player orientation can be defined as the projection (2D) of the normal vector placed in the center of the upper-torso of players (3D). This research presents a novel technique to obtain player orientation from monocular video recordings by mapping pose parts (shoulders and hips) in a 2D field by combining OpenPose with a super-resolution network, and merging the obtained estimation with contextual information (ball position). Results have been validated with players-held EPTS devices, obtaining a median error of 27 degrees/player. Moreover, three novel types of orientation maps are proposed in order to make raw orientation data easy to visualize and understand, thus allowing further analysis at team- or player-level.

Pierrick Chatillon, Coloma Ballester

Anomaly detection is a difficult problem in many areas and has recently been subject to a lot of attention. Classifying unseen data as anomalous is a challenging matter. Latest proposed methods rely on Generative Adversarial Networks (GANs) to estimate the normal data distribution, and produce an anomaly score prediction for any given data. In this article, we propose a simple yet new adversarial method to tackle this problem, denoted as History-based anomaly detector (HistoryAD). It consists of a self-supervised model, trained to recognize 'normal' samples by comparing them to samples based on the training history of a previously trained GAN. Quantitative and qualitative results are presented evaluating its performance. We also present a comparison to several state-of-the-art methods for anomaly detection showing that our proposal achieves top-tier results on several datasets.

Patricia Vitoria, Lara Raad, Coloma Ballester

The colorization of grayscale images is an ill-posed problem, with multiple correct solutions. In this paper, we propose an adversarial learning colorization approach coupled with semantic information. A generative network is used to infer the chromaticity of a given grayscale image conditioned to semantic clues. This network is framed in an adversarial model that learns to colorize by incorporating perceptual and semantic understanding of color and class distributions. The model is trained via a fully self-supervised strategy. Qualitative and quantitative results show the capacity of the proposed method to colorize images in a realistic way achieving state-of-the-art results.

Adrià Arbués-Sangüesa, Gloria Haro, Coloma Ballester

Tracking data is a powerful tool for basketball teams in order to extract advanced semantic information and statistics that might lead to a performance boost. However, multi-person tracking is a challenging task to solve in single-camera video sequences, given the frequent occlusions and cluttering that occur in a restricted scenario. In this paper, a novel multi-scale detection method is presented, which is later used to extract geometric and content features, resulting in a multi-person video tracking system. Having built a dataset from scratch together with its ground truth (more than 10k bounding boxes), standard metrics are evaluated, obtaining notable results both in terms of detection (F1-score) and tracking (MOTA). The presented system could be used as a source of data gathering in order to extract useful statistics and semantic analyses a posteriori.

Adrià Arbués-Sangüesa, Coloma Ballester, Gloria Haro

Tracking sports players is a widely challenging scenario, specially in single-feed videos recorded in tight courts, where cluttering and occlusions cannot be avoided. This paper presents an analysis of several geometric and semantic visual features to detect and track basketball players. An ablation study is carried out and then used to remark that a robust tracker can be built with Deep Learning features, without the need of extracting contextual ones, such as proximity or color similarity, nor applying camera stabilization techniques. The presented tracker consists of: (1) a detection step, which uses a pretrained deep learning model to estimate the players pose, followed by (2) a tracking step, which leverages pose and semantic information from the output of a convolutional layer in a VGG network. Its performance is analyzed in terms of MOTA over a basketball dataset with more than 10k instances.

Patricia Vitoria, Joan Sintes, Coloma Ballester

Image inpainting is the task of filling-in missing regions of a damaged or incomplete image. In this work we tackle this problem not only by using the available visual data but also by incorporating image semantics through the use of generative models. Our contribution is twofold: First, we learn a data latent space by training an improved version of the Wasserstein generative adversarial network, for which we incorporate a new generator and discriminator architecture. Second, the learned semantic information is combined with a new optimization loss for inpainting whose minimization infers the missing content conditioned by the available data. It takes into account powerful contextual and perceptual content inherent in the image itself. The benefits include the ability to recover large regions by accumulating semantic information even it is not fully present in the damaged image. Experiments show that the presented method obtains qualitative and quantitative top-tier results in different experimental situations and also achieves accurate photo-realism comparable to state-of-the-art works.

Roberto P. Palomares, Enric Meinhardt-Llopis, Coloma Ballester et al.

We propose a large displacement optical flow method that introduces a new strategy to compute a good local minimum of any optical flow energy functional. The method requires a given set of discrete matches, which can be extremely sparse, and an energy functional which locally guides the interpolation from those matches. In particular, the matches are used to guide a structured coordinate-descent of the energy functional around these keypoints. It results in a two-step minimization method at the finest scale which is very robust to the inevitable outliers of the sparse matcher and able to capture large displacements of small objects. Its benefits over other variational methods that also rely on a set of sparse matches are its robustness against very few matches, high levels of noise and outliers. We validate our proposal using several optical flow variational models. The results consistently outperform the coarse-to-fine approaches and achieve good qualitative and quantitative performance on the standard optical flow benchmarks.

Maria Oliver, Gloria Haro, Mariella Dimiccoli et al.

This paper presents a computational model to recover the most likely interpretation of the 3D scene structure from a planar image, where some objects may occlude others. The estimated scene interpretation is obtained by integrating some global and local cues and provides both the complete disoccluded objects that form the scene and their ordering according to depth. Our method first computes several distal scenes which are compatible with the proximal planar image. To compute these different hypothesized scenes, we propose a perceptually inspired object disocclusion method, which works by minimizing the Euler's elastica as well as by incorporating the relatability of partially occluded contours and the convexity of the disoccluded objects. Then, to estimate the preferred scene we rely on a Bayesian model and define probabilities taking into account the global complexity of the objects in the hypothesized scenes as well as the effort of bringing these objects in their relative position in the planar image, which is also measured by an Euler's elastica-based quantity. The model is illustrated with numerical experiments on, both, synthetic and real images showing the ability of our model to reconstruct the occluded objects and the preferred perceptual order among them. We also present results on images of the Berkeley dataset with provided figure-ground ground-truth labeling.