Fua, P.[Pascal]
Co Author Listing * Home Page.
* email: Fua, P.[Pascal]: pascal fua AT epfl ch
* 3-D Modeling of Drainage Patterns
* 3D Human Body Tracking Using Deterministic Temporal Motion Models
* 3D People Tracking with Gaussian Process Dynamical Models
* 3d Pose Based Feedback for Physical Exercises
* 3D pose refinement from reflections
* 3D tracking for gait characterization and recognition
* Accurate face models from uncalibrated and ill-lit video sequences
* Accurate Non-Iterative O(n) Solution to the PnP Problem
* Active Learning for Delineation of Curvilinear Structures
* ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture
* Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate
* Adversarial Parametric Pose Prior
* Animated Heads from Ordinary Images: A Least-Squares Approach
* Appearance-based keypoint clustering
* Are spatial and global constraints really necessary for segmentation?
* Articulated soft objects for multiview shape and motion capture
* Automated Body Modeling from Video Sequences
* Automated Delineation of Dendritic Networks in Noisy Image Stacks
* Automated reconstruction of tree structures using path classifiers and Mixed Integer Programming
* Automatic Extraction of Generic House Roofs from High Resolution Aerial Imagery
* automatic method for determining quaternion field boundaries for ball-and-socket joint limits, An
* Better Patch Stitching for Parametric Surface Reconstruction
* Beyond Cartesian Representations for Local Descriptors
* Beyond Sharing Weights for Deep Domain Adaptation
* Beyond the Pixel-Wise Loss for Topology-Aware Delineation
* Boosting Binary Keypoint Descriptors
* Bridging the Gap between Detection and Tracking for 3D Monocular Video-Based Motion Capture
* BRIEF: Binary Robust Independent Elementary Features
* BRIEF: Computing a Local Binary Descriptor Very Fast
* Capturing 3D stretchable surfaces from single images in closed form
* Cartographic Applications of Model-Based Optimization
* Classification-Based Probabilistic Modeling of Texture Transition for Fast Line Search Tracking and Delineation
* Classifier-based Contour Tracking for Rigid and Deformable Objects
* Closed-Form Solution to Non-rigid 3D Surface Registration
* Combining Geometric and Appearance Priors for Robust Homography Estimation
* Compact signatures for high-speed interest point description and matching
* Conditional Random Fields for multi-camera object detection
* Consistent Site Modeling: Imposing Hard Constraints on Deformable Models
* constrained latent variable model, A
* Context-Aware Crowd Counting
* Convex Optimization for Deformable Surface 3-D Tracking
* Counting People by Estimating People Flows
* DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo
* Deep Active Surface Models
* Deep Occlusion Reasoning for Multi-camera Multi-target Detection
* Deformable Surface Tracking Ambiguities
* Deformable Velcro(TM) Surfaces
* Deformation-Aware Unpaired Image Translation for Pose Estimation on Laboratory Animals
* Delineating trees in noisy 2D images and 3D image-stacks
* Dense Image Registration and Deformable Surface Reconstruction in Presence of Occlusions and Minimal Texture
* Detecting Flying Objects Using a Single Moving Camera
* Detecting Irregular Curvilinear Structures in Gray Scale and Color Imagery Using Multi-directional Oriented Flux
* Detecting Road Obstacles by Erasing Them
* Detecting the Unexpected via Image Resynthesis
* Developing Species Specific Vegetation Maps Using Multi-spectral Hyperspatial Imagery From Unmanned Aerial Vehicles
* DIG: Draping Implicit Garment over the Human Body
* Direct Prediction of 3D Body Poses from Motion Compensated Sequences
* Discriminative Learning of Deep Convolutional Feature Point Descriptors
* Do We Need Binary Features for 3D Reconstruction?
* Domain Adaptation for Microscopy Imaging
* Dominant orientation templates for real-time detection of texture-less objects
* DrapeNet: Garment Generation and Self-Supervised Draping
* Dynamic and scalable large scale image reconstruction
* Efficient large-scale multi-view stereo for ultra high-resolution image sets
* Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems
* Eigendecomposition-Free Training of Deep Networks with Zero Eigenvalue-Based Losses
* Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking
* EP n P: An Accurate O(n) Solution to the P n P Problem
* Estimating People Flows to Better Count Them in Crowded Scenes
* Every Smile is Unique: Landmark-Guided Diverse Smile Generation
* Exploring Ambiguities for Monocular Non-Rigid Shape Estimation
* Extracting Generic Shapes Using Model-Driven Optimization
* Fast Keypoint Recognition in Ten Lines of Code
* Fast Keypoint Recognition Using Random Ferns
* fast local descriptor for dense matching, A
* Fast Non-Rigid Surface Detection, Registration and Realistic Augmentation
* Fast Object Detection with Entropy-Driven Evaluation
* Fast Texture-Based Tracking and Delineation Using Texture Entropy
* Fast, Accurate and Consistent Modeling of Drainage and Surrounding Terrain
* Finding Object Boundaries Using Guided Gradient Ascent
* FishEyeRecNet: A Multi-context Collaborative Deep Network for Fisheye Image Rectification
* Fixed Point Probability Field for Complex Occlusion Handling
* Flight Dynamics-Based Recovery of a UAV Trajectory Using Ground Cameras
* Flying objects detection from a single moving camera
* Free-Shape Polygonal Object Localization
* From Canonical Poses to 3D Motion Capture Using a Single Camera
* From regular images to animated heads: A least squares approach
* From Ziplock Snakes to Velcro(TM) Surfaces
* Fusing online and offline information for stable 3D tracking in real-time
* GarNet++: Improving Fast and Accurate Static 3D Cloth Draping by Curvature Loss
* GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping
* GECCO: Geometrically-Conditioned Point Diffusion Models
* Generative Model for True Orthorectificatio, A
* Generic deformable implicit mesh models for automated reconstruction
* Geometric Graph Matching Using Monte Carlo Tree Search
* Geometrical graph matching using Monte Carlo tree search
* Geometry in active learning for binary and multi-class image segmentation
* Gradient Response Maps for Real-Time Detection of Textureless Objects
* Gravity as a Reference for Estimating a Person's Height From Video
* Hierarchical implicit surface joint limits for human body tracking
* Hierarchical Implicit Surface Joint Limits to Constrain Video-Based Motion Capture
* Hot or Not: Exploring Correlations between Appearance and Temperature
* Human body pose detection using Bayesian spatio-temporal templates
* Human Detection and Segmentation via Multi-view Consensus
* Human Shape and Motion from Video
* Image Matching Across Wide Baselines: From Paper to Practice
* Image Registration without Explicit Point Correspondences
* Implicit Meshes for Effective Silhouette Handling
* Implicit meshes for modeling and reconstruction
* Implicit Meshes for Surface Reconstruction
* Implicit Surfaces Make for Better Silhouettes
* ImplicitAtlas: Learning Deformable Shape Templates in Medical Imaging
* Imposing Hard Constraints on Deformable Models Through Optimization in Orthogonal Subspaces
* Imposing Hard Constraints on Soft Snakes
* Initializing Snakes
* Introducing Geometry in Active Learning for Image Segmentation
* Joint Pose Estimator and Feature Learning for Object Detection
* Joint Segmentation and Path Classification of Curvilinear Structures
* Keypoint Recognition Using Randomized Trees
* Keypoint Signatures for Fast Learning and Recognition
* Laplacian Meshes for Monocular 3D Shape Recovery
* LDAHash: Improved Matching with Smaller Descriptors
* Learning Context Cues for Synapse Segmentation
* Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets
* Learning Latent Representations of 3D Human Pose with Deep Neural Networks
* Learning Monocular 3D Human Pose Estimation from Multi-view Images
* Learning Real-Time Perspective Patch Rectification
* Learning rotational features for filament detection
* Learning Separable Filters
* Learning Separable Filters
* Learning Structured Models for Segmentation of 2-D and 3-D Imagery
* Learning to Align Sequential Actions in the Wild
* Learning to Assign Orientations to Feature Points
* Learning to Find Good Correspondences
* Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation
* Learning to Match Aerial Images with Deep Attentive Architectures
* Learning to Reconstruct Texture-Less Deformable Surfaces from a Single View
* Leveraging Self-Supervision for Cross-Domain Crowd Counting
* Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo
* LIFT: Learned Invariant Feature Transform
* LightDepth: Single-View Depth Self-Supervision from Illumination Decline
* Lightweight Multi-View 3D Pose Estimation Through Camera-Disentangled Representation
* Linear and Non-Linear Models for Monocular 3D Motion Capture
* Linear Local Models for Monocular Reconstruction of Deformable Surfaces
* Linking Pose and Motion
* Local deformation models for monocular 3D shape recovery
* Local Non-Rigid Structure-From-Motion From Diffeomorphic Mappings
* Locating Cultural Regions in Aerial Imagery using Geometric Cues
* Making Action Recognition Robust to Occlusions and Viewpoint Changes
* Making Background Subtraction Robust to Sudden Illumination Changes
* Making Snakes Converge from Minimal Initialization
* Markov-based Silhouette Extraction for Three-Dimensional Body Tracking in Presence of Cluttered Background
* Masksembles for Uncertainty Estimation
* Matching Seqlets: An Unsupervised Approach for Locality Preserving Sequence Matching
* MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks
* Model Driven Edge Detection
* Model-Based and Context-Based Vision at SRI
* Model-Based Approach to Accurate and Consistent 3-D Modeling of Drainage and Surrounding Terrain
* Model-Based Optimization: Accurate and Consistent Site Modeling
* Model-Based Optimization: An Approach to Fast, Accurate and Consistent Site Modeling
* Model-Based Silhouette Extraction for Accurate People Tracking
* Modeling Facial Geometry Using Compositional VAEs
* Modeling People Toward Vision-Based Understanding of a Person's Shape, Appearance, and Movement
* Modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
* Monocular 3-D Tracking of the Golf Swing
* Monocular 3D Reconstruction of Locally Textured Surfaces
* Monocular Model-Based 3D Tracking of Rigid Objects: A Survey
* Motion Capture from Pan-Tilt Cameras with Unknown Orientation
* Motion Prediction Using Temporal Inception Module
* Multi-camera Tracking and Atypical Motion Detection with Behavioral Maps
* Multi-Commodity Network Flow for Tracking Multiple People
* Multi-modal Mean-Fields via Cardinality-Based Clamping
* Multi-view Tracking Using Weakly Supervised Human Motion Prediction
* Multicamera People Tracking with a Probabilistic Occupancy Map
* Multiple Human Pose Estimation with Temporally Consistent 3D Pictorial Structures
* Multiple object tracking using flow linear programming
* Multiple Object Tracking Using K-Shortest Paths Optimization
* Multiscale Centerline Detection
* Multiscale Centerline Detection by Learning a Scale-Space Distance Transform
* Network Flow Integer Programming to Track Elliptical Cells in Time-Lapse Sequences
* Neural Scene Decomposition for Multi-Person Motion Capture
* Non-Linear Beam Model for Tracking Large Deformations
* Non-Markovian Globally Consistent Multi-object Tracking
* Non-Rigid Graph Registration Using Active Testing Search
* Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images, A
* Objective Functions for Feature Discrimination
* Objective Functions for Feature Discrimination: Applications to Semiautomated and Automated Feature Extraction
* Objective Functions for Feature Discrimination: Theory
* Observable subspaces for 3D human motion recovery
* On benchmarking camera calibration and multi-view stereo for high resolution imagery
* On rendering synthetic images for training an object detector
* On the relevance of sparsity for image classification
* Online learning of patch perspective rectification for efficient object detection
* Optimization Framework for Feature Extraction, An
* Overcoming the Domain Gap in Neural Action Representations
* Pareto-optimal dictionaries for signatures
* Parsing human skeletons in an operating room
* PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers
* Performance Evaluation of Local Features for Image-Based 3D Reconstruction, A
* Persistent Homology With Improved Locality Information for More Effective Delineation
* Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation
* Physically Valid Shape Parameterization for Monocular 3-D Deformable Surface Tracking
* Point matching as a classification problem for fast and robust object pose estimation
* Pose estimation for category specific multiview object localization
* Pose Priors for Simultaneously Solving Alignment and Correspondence
* Principled Parallel Mean-Field Inference for Discrete Random Fields
* Priors for People Tracking from Small Training Sets
* Probability occupancy maps for occluded depth images
* Projection onto the Manifold of Elongated Structures for Accurate Extraction
* Promoting Connectivity of Network-Like Structures by Enforcing Region Separation
* Randomized Trees for Real-Time Keypoint Recognition
* Real-time camera pose estimation for sports fields
* Real-Time Deformable Detector, A
* Real-time landing place assessment in man-made environments
* Real-time learning of accurate patch rectification
* Real-Time Non-Rigid Surface Detection
* Real-Time Seamless Single Shot 6D Object Pose Prediction
* Real-time vehicle tracking for driving assistance
* Receptive Fields Selection for Binary Feature Description
* Reconstructing Curvilinear Networks Using Path Classifiers and Integer Programming
* Reconstructing Evolving Tree Structures in Time Lapse Sequences
* Reconstructing Evolving Tree Structures in Time Lapse Sequences by Enforcing Time-Consistency
* Reconstructing Loopy Curvilinear Structures Using Integer Programming
* Reconstructing sharply folding surfaces: A convex formulation
* Recurrent U-Net for Resource-Constrained Segmentation
* Refining Mitochondria Segmentation in Electron Microscopy Imagery with Active Surfaces
* Registration without Correspondences
* Regularized Bundle-Adjustment to Model Heads from Image Sequences without Calibration Data
* Resegmentation Using Generic Shape: Locating General Cultural Objects
* Residual Parameter Transfer for Deep Domain Adaptation
* Resolving occlusion in multiframe reconstruction of deformable surfaces
* Retrieving multiple light sources in the presence of specular reflections and texture
* Robust 3D Object Tracking from Monocular Images Using Stable Parts
* Robust data association for online applications
* Robust Differentiable SVD
* Robust Multi-View Change Detection
* Robust non-rigid registration of 2D and 3D graphs
* Robust People Tracking with Global Trajectory Optimization
* Segmentation-Driven 6D Object Pose Estimation
* Self-Consistency and MDL: A Paradigm for Evaluating Point-Correspondence Algorithms, and Its Application to Detecting Changes in Surface Elevation
* Self-Consistency: A Novel Approach to Characterizing the Accuracy and Reliability of Point Correspondence Algorithms
* Self-Supervised Human Detection and Segmentation via Background Inpainting
* Shape Reconstruction by Learning Differentiable Surface Representations
* Simultaneous point matching and 3D deformable surface reconstruction
* Simultaneous pose, correspondence and non-rigid shape
* Simultaneous Recognition and Homography Extraction of Local Patches with a Simple Linear Classifier
* Single-Stage 6D Object Pose Estimation
* Site-Model Construction Component of the RADIUS Testbed System, The
* Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches
* SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
* Social Scene Understanding: End-to-End Multi-person Action Localization and Collective Activity Recognition
* Spatio-chromatic decorrelation by shift-invariant filtering
* Stable Real-Time 3D Tracking Using Online and Offline Information
* Stochastic Exploration of Ambiguities for Nonrigid Shape Recovery
* Structured Image Segmentation Using Kernelized Features
* Structured Prediction of 3D Human Pose with Deep Neural Networks
* Supervoxel-Based Segmentation of Mitochondria in EM Image Stacks With Learned Shape Features
* Surface Deformation Models for Nonrigid 3D Shape Recovery
* Take your eyes off the ball: Improving ball-tracking by focusing on team play
* Template-Based Monocular 3D Shape Recovery Using Laplacian Meshes
* Template-free Monocular Reconstruction of Deformable Surfaces
* Temporal motion models for monocular and multiview 3D human body tracking
* Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation
* Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases
* Texture Boundary Detection for Real-Time Tracking
* Thick boundaries in binary space and their influence on nearest-neighbor search
* TILDE: A Temporally Invariant Learned DEtector
* TopoAL: An Adversarial Learning Approach for Topology-aware Road Segmentation
* Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial Images
* TPAMI CVPR Special Section
* Tracking and Modeling People in Video Sequences
* Tracking articulated bodies using Generalized Expectation Maximization
* Tracking Interacting Objects Optimally Using Integer Programming
* Tracking Interacting Objects Using Intertwined Flows
* Tracking multiple people under global appearance constraints
* Training for Task Specific Keypoint Detection
* Two-level Data Augmentation for Calibrated Multi-view Detection
* Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation
* Using Contextual Information to Set Control Parameters of a Vision Process
* Using Dirichlet Free Form Deformation to Fit Deformable Models to Noisy 3-D Data
* Using Generic Geometric Models for Intelligent Shape Extraction
* Using Model-Driven Bundle-Adjustment to Model Heads from Raw Video Sequences
* Using Specularities to Recover Multiple Light Sources in the Presence of Texture
* Velcro Surfaces: Fast Initialization of Deformable Models
* Visual Correspondences for Unsupervised Domain Adaptation on Electron Microscopy Images
* Visual Golf Club Tracking for Enhanced Swing Analysis
* What Face and Body Shapes Can Tell Us About Height
* What Players do with the Ball: A Physically Constrained Interaction Modeling
* Wide-Depth-Range 6D Object Pose Estimation in Space
* WILDTRACK: A Multi-camera HD Dataset for Dense Unscripted Pedestrian Detection
* Worldwide Pose Estimation Using 3D Point Clouds
* Ziplock Snakes
Includes: Fua, P.[Pascal] Fua, P.
294 for Fua, P.
Fua, P.V.[Pascal V.]
Co Author Listing * 3D Face Modeling from Stereo and Differential Constraints
* 3D stereo reconstruction of human faces driven by differential constraints
* Articulated Soft Objects for Video-based Body Modeling
* Combining Stereo and Monocular Information to Compute Dense Depth Maps That Preserve Depth Discontinuities
* Combining Stereo, Shading, and Geometric Constraints for Surface Reconstruction from Multiple Views
* Context-Based Vision
* Detecting Changes in 3-D Shape using Self-Consistency
* framework for detecting changes in terrain, A
* From Multiple Stereo Views to Multiple 3-D Surfaces
* From Points to Surfaces
* Incorporating Differential Constraints in a 3D Reconstruction Process. Application to Stereo
* Measuring the Self-Consistency of Stereo Algorithms
* Method and system for detecting changes in three dimensional shape
* Object-Centered Surface Reconstruction: Combining Multi-Image Stereo and Shading
* Parallel Stereo Algorithm That Produces Dense Depth Maps and Preserves Image Features, A
* Radiometry of Multiple Images, The
* Reconstructing Complex Surfaces from Multiple Stereo Views
* Reconstructing Surfaces from Unstructured 3D Points
* Recovery of Reflectances and Varying Illuminants from Multiple Views
* Segmenting Unstructured 3D Points into Surfaces
* Some Computational Strategies for Object Recognition
* Stereo Reconstruction from Multiple Views
* Taking Advantage of Image-Based and Geometry-Based Constraints to Recover 3-D Surfaces
* Unified Framework to Recover 3-D Surfaces by Combining Image-Based and Externally-Supplied Constraints, A
* Using 3-Dimensional Meshes to Combine Image-Based and Geometry-Based Constraints
* Using Crest Lines to Guide Surface Reconstruction from Stereo
* Using differential constraints to generate a 3D face model from stereo
* Using Differential Constraints to Reconstruct Complex Surfaces from Stereo
* Using Differential Properties for Stereo Reconstruction of Complex Surfaces
* Variable Albedo Surface Reconstruction from Stereo and Shape from Shading
Includes: Fua, P.V.[Pascal V.] Fua, P.V.
30 for Fua, P.V.