Abstract: In this talk, we’ll explore image understanding from a material-centric perspective, namely through the lens of material appearance. Materials distinguish themselves by their response to light, which is governed and modelled through physical properties like roughness or gloss – however, understanding such properties is a non-trivial task for current models and network architectures. We’ll … Read more
📅 Date: May 20🕦 Time: 11:30📍 Location: CVC Conference Room (Centre de Visió per Computador) Abstract: As CVPR 2026 approaches and CVC has multiple papers and workshops accepted this year, we are organizing an Internal Pre-CVPR Seminar to showcase selected contributions from our researchers. During the session, CVC researchers will present a set of papers … Read more
Abstract: (TBD) Short bio: Chaker Larabi is a Full Professor at Université de Poitiers, in the XLIM CNRS institute, where he is head of the ASALI research axis. He received his PhD from the University of Poitiers in 2002. His scientific interests span different fields of image and video processing, including quality assessment, compression, optimization, … Read more
Abstract: The seminar will introduce my artistic practice and research, which explores how ubiquitous technologies can be used to reveal their own material, sensory, and image-making capacities. Through works made with scanners, robotic vacuums, window-cleaning robots, computer mice, printers, smartphone sensors, and thermal paper, I investigate how devices record, respond to, and interact with the … Read more
Abstract: This talk will present an experimental study on the behaviour, scalability, and generative quality of Denoising Diffusion Probabilistic Models (DDPMs) for image synthesis across datasets of increasing complexity. Three case studies are analysed and compared based on FID (Fréchet Inception Distance) evaluation metric and the performance of downstream classifiers to discriminate the synthetically generated … Read more
Abstract: Neural networks (NNs) excel across a wide range of machine learning tasks due to their flexibility and scalability, but they also pose challenges in privacy, interpretability, robustness, and efficiency—limitations that can be especially critical for large models trained on sensitive data. To tackle these issues, we propose the use of tensor network models. In … Read more
Abstract: I will start by introducing DTLR, our general approach for recognizing text lines, whether printed (OCR) or handwritten (HTR), using Latin, Chinese, or ciphered characters. Most HTR methods have focused on autoregressive decoding, which predicts characters one at a time. In contrast, DTLR processes the entire line at once. Our method shows strong results … Read more
Abstract: We live in a world where all interactions with the environment necessitate a 3D understanding of our surroundings. While humans excel at reasoning about 3D structures from both multi-view and single-view images, replicating this capability in computers remains challenging due to the need to combine mathematically proven geometric knowledge with end-to-end learned priors. In … Read more
Abstract: This presentation provides a short overview of the research conducted by the computer vision research group in Amsterdam (UvA – University of Amsterdam) featuring various research projects and several commercially applied use cases.
Abstract: This presentation is divided into two interconnected parts, exploring the applications and inner workings of Vision-Language contrastive models, with a focus on CLIP-like architectures. In the first part, we examine the application of these models to semantic segmentation tasks. We begin with a brief overview of our previous work in semantic segmentation and multi-branched … Read more