Pascal Fua
YOU?
Author Swipe
View article: High Resolution UDF Meshing via Iterative Networks
High Resolution UDF Meshing via Iterative Networks Open
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 neura…
View article: End-to-End 4D Heart Mesh Recovery Across Full-Stack and Sparse Cardiac MRI
End-to-End 4D Heart Mesh Recovery Across Full-Stack and Sparse Cardiac MRI Open
Reconstructing cardiac motion from CMR sequences is critical for diagnosis, prognosis, and intervention. Existing methods rely on complete CMR stacks to infer full heart motion, limiting their applicability during intervention when only sp…
View article: High-Fidelity and Generalizable Neural Surface Reconstruction with Sparse Feature Volumes
High-Fidelity and Generalizable Neural Surface Reconstruction with Sparse Feature Volumes Open
Generalizable neural surface reconstruction has become a compelling technique to reconstruct from few images without per-scene optimization, where dense 3D feature volume has proven effective as a global representation of scenes. However, …
View article: A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields
A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields Open
Neural Radiance Fields (NeRF) has emerged as a compelling framework for scene representation and 3D recovery. To improve its performance on real-world data, depth regularizations have proven to be the most effective ones. However, depth es…
View article: A novel immersive catheter ablation simulator based on individualized 3D MR patients' heart models improves ablation performance of future electrophysiologists
A novel immersive catheter ablation simulator based on individualized 3D MR patients' heart models improves ablation performance of future electrophysiologists Open
Background Arrhythmias are rising worldwide due to population aging. Efficient training of next generation of electrophysiologists (EPs) to perform catheter (cath) ablation (CA) of arrhythmias is needed. Dedicated simulators for EP trainin…
View article: Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates
Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates Open
Reconstructing 3D clothed humans from images is fundamental to applications like virtual try-on, avatar creation, and mixed reality. While recent advances have enhanced human body recovery, accurate reconstruction of garment geometry -- es…
View article: PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimization
PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimization Open
Accurate 3D shape representation is essential in engineering applications such as design, optimization, and simulation. In practice, engineering workflows require structured, part-based representations, as objects are inherently designed a…
View article: Vision-based power line cables and pylons detection for low flying aircraft
Vision-based power line cables and pylons detection for low flying aircraft Open
Power lines are dangerous for low-flying aircraft, especially in low-visibility conditions. Thus, a vision-based system able to analyze the aircraft’s surroundings and to provide the pilots with a “second pair of eyes” can contribute to en…
View article: Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT
Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT Open
Our approach shows potential for improving BOS diagnosis by enabling early detection and management. The ability to detect BOS from standard-resolution scans at any stage of respiration makes this method more accessible than previous appro…
View article: Training in a novel immersive catheter ablation simulator using 3D MR heart models of individual patients improves performance of future electrophysiologists
Training in a novel immersive catheter ablation simulator using 3D MR heart models of individual patients improves performance of future electrophysiologists Open
View article: Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures
Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures Open
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…
View article: MedTet: An Online Motion Model for 4D Heart Reconstruction
MedTet: An Online Motion Model for 4D Heart Reconstruction Open
We present a novel approach to reconstruction of 3D cardiac motion from sparse intraoperative data. While existing methods can accurately reconstruct 3D organ geometries from full 3D volumetric imaging, they cannot be used during surgical …
View article: Counting Stacked Objects
Counting Stacked Objects Open
Visual object counting is a fundamental computer vision task underpinning numerous real-world applications, from cell counting in biomedicine to traffic and wildlife monitoring. However, existing methods struggle to handle the challenge of…
View article: No Identity, no problem: Motion through detection for people tracking
No Identity, no problem: Motion through detection for people tracking Open
Tracking-by-detection has become the de facto standard approach to people tracking. To increase robustness, some approaches incorporate re-identification using appearance models and regressing motion offset, which requires costly identity …
View article: Gradient Distance Function
Gradient Distance Function Open
Unsigned Distance Functions (UDFs) can be used to represent non-watertight surfaces in a deep learning framework. However, UDFs tend to be brittle and difficult to learn, in part because the surface is located exactly where the UDF is non-…
View article: Efficient anatomical labeling of pulmonary tree structures via deep point-graph representation-based implicit fields
Efficient anatomical labeling of pulmonary tree structures via deep point-graph representation-based implicit fields Open
Pulmonary diseases rank prominently among the principal causes of death worldwide. Curing them will require, among other things, a better understanding of the complex 3D tree-shaped structures within the pulmonary system, such as airways, …
View article: A Latent Implicit 3D Shape Model for Multiple Levels of Detail
A Latent Implicit 3D Shape Model for Multiple Levels of Detail Open
Implicit neural representations map a shape-specific latent code and a 3D coordinate to its corresponding signed distance (SDF) value. However, this approach only offers a single level of detail. Emulating low levels of detail can be achie…
View article: Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields
Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields Open
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 po…
View article: Author Correction: BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets
Author Correction: BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets Open
View article: DeepGeo: Deep Geometric Mapping for Automated and Effective Parameterization in Aerodynamic Shape Optimization
DeepGeo: Deep Geometric Mapping for Automated and Effective Parameterization in Aerodynamic Shape Optimization Open
Aerodynamic shape optimization (ASO) is a key technique in aerodynamic designs, aimed at enhancing an object's physical performance while adhering to specific constraints. Traditional parameterization methods for ASO often require substant…
View article: Neural Surface Detection for Unsigned Distance Fields
Neural Surface Detection for Unsigned Distance Fields Open
Extracting surfaces from Signed Distance Fields (SDFs) can be accomplished using traditional algorithms, such as Marching Cubes. However, since they rely on sign flips across the surface, these algorithms cannot be used directly on Unsigne…
View article: Vision-Based Power Line Cables and Pylons Detection for Low Flying Aircraft
Vision-Based Power Line Cables and Pylons Detection for Low Flying Aircraft Open
Power lines are dangerous for low-flying aircraft, especially in low-visibility conditions. Thus, a vision-based system able to analyze the aircraft's surroundings and to provide the pilots with a "second pair of eyes" can contribute to en…
View article: CLOAF: CoLlisiOn-Aware Human Flow
CLOAF: CoLlisiOn-Aware Human Flow Open
Even the best current algorithms for estimating body 3D shape and pose yield results that include body self- intersections. In this paper, we present CLOAF, which exploits the diffeomorphic nature of Ordinary Differential Equations to elim…
View article: Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature Alignment
Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature Alignment Open
Animal Re-ID is crucial for wildlife conservation, yet it faces unique challenges compared to person Re-ID. First, the scarcity and lack of diversity in datasets lead to background-biased models. Second, animal Re-ID depends on subtle, spe…
View article: Reconstruction of Manipulated Garment with Guided Deformation Prior
Reconstruction of Manipulated Garment with Guided Deformation Prior Open
Modeling the shape of garments has received much attention, but most existing approaches assume the garments to be worn by someone, which constrains the range of shapes they can assume. In this work, we address shape recovery when garments…
View article: A Closed-Form, Pairwise Solution to Local Non-Rigid Structure-From-Motion
A Closed-Form, Pairwise Solution to Local Non-Rigid Structure-From-Motion Open
A recent trend in Non-Rigid Structure-from-Motion (NRSfM) is to express local, differential constraints between pairs of images, from which the surface normal at any point can be obtained by solving a system of polynomial equations. While …
View article: MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering
MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering Open
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. o…
View article: DataCook: Crafting Anti-Adversarial Examples for Healthcare Data Copyright Protection
DataCook: Crafting Anti-Adversarial Examples for Healthcare Data Copyright Protection Open
In the realm of healthcare, the challenges of copyright protection and unauthorized third-party misuse are increasingly significant. Traditional methods for data copyright protection are applied prior to data distribution, implying that mo…
View article: Enabling Uncertainty Estimation in Iterative Neural Networks
Enabling Uncertainty Estimation in Iterative Neural Networks Open
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 conver…
View article: LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models
LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models Open
Patient data from real-world clinical practice often suffers from data scarcity and long-tail imbalances, leading to biased outcomes or algorithmic unfairness. This study addresses these challenges by generating lesion-containing image-seg…