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.

A common assumption in machine vision is that the training and test samples are drawn from the same distribution. However, there are many problems when this assumption is grossly violated, as in bio-medical applications where different acquisitions can gen ...

We propose an active learning approach to image segmentation that exploits geometric priors to speed up and streamline the annotation process. It can be applied for both background foreground and multi-class segmentation tasks in 2D images and 3D image vol ...

A new learning strategy for object detection is presented. The proposed scheme forgoes the need to train a collection of detectors dedicated to homogeneous families of poses, and instead learns a single classifier that has the inherent ability to deform ba ...

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

Serial electron microscopy imaging is crucial for exploring the structure of cells and tissues. The development of block face scanning electron microscopy methods and their ability to capture large image stacks, some with near isotropic voxels, is proving ...

In this paper, we propose a novel unsupervised approach for sequence matching by explicitly accounting for the locality properties in the sequences. In contrast to conventional approaches that rely on frame-to-frame matching, we conduct matching using sequ ...

Persistent Homology (PH) has been successfully used to train networks to detect curvilinear structures and to improve the topological quality of their results. However, existing methods are very global and ignore the location of topological features. In th ...

Orthographic images compose an efficient and economic way to represent aerial images. This kind of information allows to measure two-dimensional objects and relate these to Geographic Information Systems. This paper deals with the computation of a true ort ...

SIFT-like local feature descriptors are ubiquitously employed in such computer vision applications as content-based retrieval, video analysis, copy detection, object recognition, photo-tourism and 3D reconstruction. Feature descriptors can be designed to be invariant to certain classes of photometric and geometric transformations, in particular, affine and intensity scale transformations. However, real transformations that an image can undergo can only be approximately modeled in this way, and thus most des

This paper describes a pipeline for automatically generating level of detail (LOD) models (digital twins), specifically LOD2 and LOD3, from free-standing buildings. Our approach combines structure from motion (SfM) with deep-learning-based segmentation tec ...

We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed su ...

Background: Maximum Intensity Projections (MIP) of neuronal dendritic trees obtained from confocal microscopy are frequently used to study the relationship between tree morphology and mechanosensory function in the model organism C. elegans. Extracting den ...

Traditional aerodynamic shape optimization (ASO) is costly and time-intensive, requiring extensive manual tuning for parameterization to define the design space and manipulate geometries. Conventional parameterization methods limit flexibility and demand s ...

We propose an approach for on-line detection of small Unmanned Aerial Vehicles (UAVs) and estimation of their relative positions and velocities in the 3D environment from a single moving camera in the context of sense and avoid systems. This problem is cha ...

We propose an Active Learning approach to training a segmentation classifier that exploits geometric priors to streamline the annotation process in 3D image volumes. To this end, we use these priors not only to select voxels most in need of annotation but ...

Generative design can rapidly propose diverse, constraint-satisfying candidates for real-time analysis and closed-loop optimization under expensive physics evaluations. However, reliable generation requires effective incorporation of physical constraints by means of physics-guided generation. In many state-of-the-art physics-guided flow-based methods, physical optimization cannot fully converge within the generative time schedule, leading to limited constraint-satisfaction accuracy in the generated samples.

Real-time free-view human rendering from sparse-view RGB inputs is a challenging task due to the sensor scarcity and the tight time budget. To ensure efficiency, recent methods leverage 2D CNNs operating in texture space to learn rendering primitives. Howe ...

Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they still need a suf ...

BackgroundBronchiolitis Obliterans Syndrome (BOS), a fibrotic airway disease that may develop after lung transplantation, conventionally relies on pulmonary function tests (PFTs) for diagnosis due to limitations of CT imaging. Deep neural networks (DNNs) h ...

Unsigned Distance Fields (UDFs) are a natural implicit representation for open surfaces but, unlike Signed Distance Fields (SDFs), are challenging to triangulate into explicit meshes. This is especially true at high resolutions where neural UDFs exhibit higher noise levels, which makes it hard to capture fine details. Most current techniques perform within single voxels without reference to their neighborhood, resulting in missing surface and holes where the UDF is ambiguous or noisy. We show that this can

Pascal Fua

Chat with Graph Search

Non-Linear Domain Adaptation with Boosting

Geometry in active learning for binary and multi-class image segmentation

Joint Pose Estimator and Feature Learning for Object Detection

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

NeuroMorph: A Toolset for the Morphometric Analysis and Visualization of 3D Models Derived from Electron Microscopy Image Stacks

Matching Seqlets: An Unsupervised Approach for Locality Preserving Sequence Matching

Persistent Homology with Improved Locality Information for more Effective Delineation

A Generative Model for True Orthorectification

LDAHash: Improved matching with smaller descriptors

Generating LOD3 building models from structure-from-motion and semantic segmentation

Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases

Dendritic tree extraction from noisy maximum intensity projection images in C-elegans

Automated Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Vision-Based Unmanned Aerial Vehicle Detection and Tracking for Sense and Avoid Systems

Introducing Geometry in Active Learning for Image Segmentation

Physics-guided generative design with gradient-based source-space optimization on flow matching

Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures

Unsupervised Geometry-Aware Representation Learning for 3D Human Pose Estimation

Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT

High Resolution UDF Meshing via Iterative Networks