Publications by Pascal Fua | EPFL Graph Search

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

We propose a fast texture-segmentation approach to the problem of 2-D and 3--D model-based contour tracking, which is suitable for real-time or interactive applications. Our approach relies on detecting texture boundaries in the direction normal to the contour boundaries and on using a Hidden Markov Model to link these boundary points in the other direction. The probabilities that appear in this computation closely relate to texture entropy and Kullback-Leibler Divergence, a property we use to compute and u

Latent variable models provide valuable compact representations for learning and inference in many computer vision tasks. However, most existing models cannot directly encode prior knowledge about the specific problem at hand. In this paper, we introduce a constrained latent variable model whose generated output inherently accounts for such knowledge. To this end, we propose an approach that explicitly imposes equality and inequality constraints on the model's output during learning, thus avoiding the compu

Implicit functions have significantly advanced shape modeling in diverse fields. Yet, their application within medical imaging often overlooks the intricate interrelations among various anatomical structures, a consideration crucial for accurately modeling complex multi-part structures like the heart. This study presents ImHeart, a latent variable model specifically designed to model complex heart structures. Leveraging the power of learnable templates, ImHeart adeptly captures the intricate relationships b

Recovering the light sources from images in which the objects can move is difficult both because the specularities travel along the surfaces and because diffuse reflections do not remain constant. In this paper, we show that this can nevertheless be done without making the very restrictive assumptions that are usually made provided that 3D models of some scene objects are available or can be computed. Our approach involves following local gray-level maxima and deciding whether or not they represent specular

We present a template-based approach to detecting human silhouettes in a specific walking pose. Our templates consist of short sequences of 2D silhouettes obtained from motion capture data. This lets us incorporate motion information into them and helps di ...

We propose a vision based real-time object recognition system, that provides object identification and 3D position data for the automatic initialization of a 3D tracking system. A-priori information is generated using the models of objects which may be present in the image. During recognition this data is accessed, using the position of corner features in the video image for indexing. A voting scheme is used to recognize objects and their positions in a single run. Upon recognition, a 3D object tracker can

Most recent 6D pose estimation frameworks first rely on a deep network to establish correspondences between 3D object keypoints and 2D image locations and then use a variant of a RANSAC-based Perspective-n-Point (PnP) algorithm. This two-stage process, how ...

Simulating realistic sensors is a challenging part in data generation for autonomous systems, often involving carefully handcrafted sensor design, scene properties, and physics modeling. To alleviate this, we introduce a pipeline for data-driven simulation ...

We presented an approach for speeding-up image acquisition when tasked with localizing specific structures in FIB-SEM imagery. It exploits the fact that low-quality images can be acquired faster than higher-quality ones and yet be sufficient for inference ...

We present a new approach for large scale multi-view stereo matching, which is designed to operate on ultra high resolution image sets and efficiently compute dense 3D point clouds. We show that, by using a robust descriptor for matching purposes and high ...

Most recent approaches to monocular non-rigid 3D shape recovery rely on exploiting point correspondences and work best when the whole surface is well-textured. The alternative is to rely either on contours or shading information, which has only been demonstrated in very restrictive settings. Here, we propose a novel approach to monocular deformable shape recovery that can operate under complex lighting and handle partially textured surfaces. At the heart of our algorithm are a learned mapping from intensity

While Physics-Based Simulation (PBS) can accurately drape a 3D garment on a 3D body, it remains too costly for real-time applications, such as virtual try-on. By contrast, inference in a deep network, requiring a single forward pass, is much faster. Taking ...

Data augmentation has proven its usefulness to improve model generalization and performance. While it is commonly applied in computer vision application when it comes to multi-view systems, it is rarely used. Indeed geometric data augmentation can break th ...

We present a novel probabilistic approach to fully automated delineation of tree structures in noisy 2D images and 3D image stacks. Unlike earlier methods that rely mostly on local evidence, ours builds a set of candidate trees over many different subsets ...

This paper presents an affordable, fully automated and accurate mapping solutions based on ultra-light UAV imagery. Several datasets are analysed and their accuracy is estimated. We show that the accuracy highly depends on the ground resolution (flying hei ...

The human annotations are imperfect, especially when produced by junior practitioners. Multi-expert consensus is usually regarded as golden standard, while this annotation protocol is too expensive to implement in many real-world projects. In this study, w ...

Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks. Yet in practice, people, no matter how conscientious, have trouble precisely delineating in 3D and on a large scale, in part because the data i ...

Most state-of-the-art approaches to action recognition rely on global representations either by concatenating local information in a long descriptor vector or by computing a single location independent histogram. This limits their performance in presence o ...

We present a new approach for the automated segmentation of excitatory synapses in image stacks acquired by electron microscopy. We rely on a large set of image features specifically designed to take spatial context into account and train a classifier that ...

This paper presents an affordable, fully automated and accurate mapping solutions based on ultra-light UAV imagery, which is commercialized by Pix4D. We show interesting application in the field of UAV mapping, analyse the accuracy of the automated processing on several datasets. The accuracy highly depends on the ground resolution (flying height) of the input imagery. When chosen appropriately this mapping solution can compete with traditional mapping solutions that capture fewer high-resolution images fro

Pascal Fua

Chat with Graph Search

Fast Texture-Based Tracking and Delineation Using Texture Entropy

A Constrained Latent Variable Model

Generating Anatomically Accurate Heart Structures via Neural Implicit Fields

Multiple Light Sources Recovery in the Presence of Specularities and Texture

Human body pose detection using Bayesian spatio-temporal templates

Real-Time 3D Object Recognition for Automatic Tracker Initialization

Single-Stage 6D Object Pose Estimation

Learning to Simulate Realistic LiDARs

Efficient scanning for em based target localization

Efficient Large Scale Multi-View Stereo for Ultra High Resolution Image Sets

Monocular 3D Reconstruction of Locally Textured Surfaces

GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping

Two-level Data Augmentation for Calibrated Multi-view Detection

Automated Reconstruction of Dendritic and Axonal Trees by Global Optimization with Geometric Priors

The Accuracy of Automatic Photogrammetric Techniques on Ultra-light UAV Imagery

Neural Annotation Refinement: Development of a New 3D Dataset for Adrenal Gland Analysis

Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate

Making Action Recognition Robust to Occlusions and Viewpoint Changes

Learning Context Cues for Synapse Segmentation in EM Volumes

AUTOMATIC MAPPING FROM ULTRA-LIGHT UAV IMAGERY