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.

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured. By contrast, recovering the 3D shape of texture-less surfaces remains an open problem, a ...

In many 3-D object-detection and pose-estimation problems, run-time performance is of critical importance. However, there usually is time to train the system. We introduce an approach that takes advantage of this fact by formulating wide-baseline matching of keypoints extracted from the input images to those found in the model images as a classification problem. This shifts much of the computational burden to a training phase and eliminates the need for expensive patch preprocessing, without sacrificing rec

The problem of estimating a surface shape from its observed reflectance properties still remains a challenging task in computer vision. The presence of global illumination effects such as inter-reflections or cast shadows makes the task particularly diffic ...

We present an Unsupervised Domain Adaptation strategy to compensate for domain shifts on Electron Microscopy volumes. Our method aggregates visual correspondences—motifs that are visually similar across different acquisitions—to infer changes on the parame ...

It is becoming increasingly clear that mitochondria play an important role in neural function. Recent studies show mitochondrial morphology to be crucial to cellular physiology and synaptic function and a link between mitochondrial defects and neuro-degene ...

Radiance Fields have become a powerful tool for modeling 3D scenes from multiple images. However, they remain difficult to segment into semantically meaningful regions. Some methods work well using 2D semantic masks, but they generalize poorly to class-agnostic segmentations. More recent methods circumvent this issue by using contrastive learning to optimize a high-dimensional 3D feature field instead. However, recovering a segmentation then requires clustering and fine-tuning the associated hyperparameters

Accurate medical image segmentation is crucial for precise anatomical delineation. Deep learning models like U-Net have shown great success but depend heavily on large datasets and struggle with domain shifts, complex structures, and limited training samples. Recent studies have explored diffusion models for segmentation by iteratively refining masks. However, these methods still retain the conventional image-to-mask mapping, making them highly sensitive to input data, which hampers stability and generaliza

Background Arrhythmias are rising worldwide owing to population aging. Efficient ablation training of next-generation electrophysiologists (EPs) is crucial. Dedicated simulators for EP training based on individual patient anatomy do not exist yet. Objective This study aimed to assess the potential training effects of a novel advanced augmented reality (AAR)–based simulator for ablations. Methods An AAR-based simulator (ADIS SA, Lausanne, Switzerland) tracks the movements of a physical ablation catheter (Imr

Coloring books capture the imagination of children and provide them with one of their earliest opportunities for creative expression. However, given the proliferation and popularity of digital devices, real-world activities like coloring can seem unexcitin ...

We propose a method for learning non-linear face geometry representations using deep generative models. Our model is a variational autoencoder with multiple levels of hidden variables where lower layers capture global geometry and higher ones encode more l ...

The ability to obtain three-dimensional (3-D) information about morphologies of nanostructures elucidates many interesting properties of materials in both physical and biological sciences. Here we demonstrate a novel method in scanning transmission electro ...

Deep learning is becoming increasingly pervasive within the fluid mechanics community. However, it continues to face resistance due to the difficulty of predicting its generalization behavior. This challenge can be partially addressed by training models that know when they are wrong—that is, models capable of providing meaningful estimates of uncertainty alongside their predictions. Although uncertainty quantification is a well-established area in the deep learning literature, it has yet to gain widespread

There has been much effort invested in increasing the robustness of human body tracking by incorporating motion models. Most approaches are probabilistic in nature and seek to avoid becoming trapped into local minima by considering multiple hypotheses, which typically requires exponentially large amounts of computation as the number of degrees of freedom increases. By contrast, in this paper, we use temporal motion models based on Principal Component Analysis to formulate the tracking problem as one of mini

Statistical learning techniques have been used to dramatically speed-up keypoint matching by training a classifier to recognize a specific set of keypoints. However, the training itself is usually relatively slow and performed offline. Although methods hav ...

Faithful human performance capture and free-view rendering from sparse RGB observations is a long-standing problem in Vision and Graphics. The main challenges are the lack of observations and the inherent ambiguities of the setting, e.g. occlusions and dep ...

SIFT-like local feature descriptors are ubiquitously employed in computer vision applications such as content-based retrieval, video analysis, copy detection, object recognition, photo tourism, and 3D reconstruction. Feature descriptors can be designed to ...

We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a coarse 3D model of the target object. These parameters can then be reused to generate an unlimited number of training images of the object of interest in arbitrary 3D poses, which can then be used to increase classification performances. A key insight of our approach is tha

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outlie ...

We propose a new formulation to the non-rigid structure-from-motion problem that only requires the deforming surface to meaning that its differential structure is preserved. This is a much weaker assumption than the traditional ones of isometry or conforma ...

Pascal Fua

Chat with Graph Search

Enabling Uncertainty Estimation in Iterative Neural Networks

Learning to Reconstruct Texture-less Deformable Surfaces from a Single View

Keypoint Recognition using Random Forests and Random Ferns

Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo

Visual Correspondences for Unsupervised Domain Adaptation on Electron Microscopy Images

Supervoxel-Based Segmentation of Mitochondria in EM Image Stacks with Learned Shape Features

Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields

DiffAtlas: GenAI-Fying Atlas Segmentation via Image-Mask Diffusion

Training in a novel advanced augmented reality-based ablation simulator: Using 3-dimensional magnetic resonance heart models of individual patients improves performance of future electrophysiologists

Live Texturing of Augmented Reality Characters from Colored Drawings

Modeling Facial Geometry using Compositional VAEs

Tilt-less 3-D electron imaging and reconstruction of complex curvilinear structures

Empirical uncertainty quantification in deep learning: Applications to fluid dynamics

3D human body tracking using deterministic temporal motion models

Keypoint Signatures for Fast Learning and Recognition

MetaCap: Meta-learning Priors from Multi-view Imagery for Sparse-View Human Performance Capture and Rendering

LDAHash: Improved Matching with Smaller Descriptors

On Rendering Synthetic Images for Training an Object Detector

Learning to Find Good Correspondences

Local Non-Rigid Structure-from-Motion from Locally Diffeomorphic Mappings