Publications related to A Non-Stationary Subdivision Scheme for the Construction of Deformable Models with Sphere-Like Topology

Related publications (34)

Neural Garment Modeling

The digitization of 3D deformable objects remains a significant challenge in computer graphics and vision, particularly in the accurate modeling of garments. Garments exhibit complex shape variability, non-rigid deformations, and frequent self-occlusion, m ...

EPFL2025

Efficient Pyramidal Analysis of Gigapixel Images on a Decentralized Modest Computer Cluster

Anne-Marie Kermarrec, Rafael Pereira Pires, Rishi Sharma

Analyzing gigapixel images is recognized as computationally demanding. In this paper, we introduce PyramidAI, a technique for analyzing gigapixel images with reduced computational cost. The proposed approach adopts a gradual analysis of the image, beginnin ...

Springer Nature Switzerland2025

Replication of soil analogues at the original scale by 3D printing: Quantitative assessment of accuracy and repeatability of the pore structural heterogeneity

Filippo Miele

The present study investigates the quality of four three-dimensional (3D) printing technologies to accurately reproduce the complex pore structure of a real undisturbed soil sample for laboratory experiments of transport in porous media at a 1:1 scale. Fou ...

ELSEVIER SCI LTD2024

NOPE: Novel Object Pose Estimation from a Single Image

Mathieu Salzmann

The practicality of 3D object pose estimation remains limited for many applications due to the need for prior knowledge of a 3D model and a training period for new objects. To address this limitation, we propose an approach that takes a single image of a n ...

IEEE2024

Semantic Shape Editing with Parametric Implicit Templates

Uday Kusupati

We propose a semantic shape editing method to edit 3D triangle meshes using parametric implicit surface templates, benefiting from the many advantages offered by analytical implicit representations, such as infinite resolution and boolean or blending opera ...

ACM Association for Computing Machinery2024

3D diffractive optics for linear interconnects and nonlinear processing

Niyazi Ulas Dinç

The optical domain presents potential avenues for enhancing both computing and communication due to its inherent properties of bandwidth, parallelism, and energy efficiency. This research focuses on harnessing 3-Dimensional (3D) diffractive optics for nove ...

EPFL2024

Machine-Learning-Enhanced Procedural Modeling for 4D Historical Cities Reconstruction

Frédéric Kaplan, Isabella Di Lenardo, Rémi Guillaume Petitpierre, Beatrice Vaienti

The generation of 3D models depicting cities in the past holds great potential for documentation and educational purposes. However, it is often hindered by incomplete historical data and the specialized expertise required. To address these challenges, we p ...

2023

Deep Learning for 3D Surface Modelling and Reconstruction

Benoît Alain René Guillard

In recent years, there has been a significant revolution in the field of deep learning, which has demonstrated its effectiveness in automatically capturing intricate patterns from large datasets. However, the majority of these successes in Computer Vision ...

EPFL2023

Automated image-based generation of finite element models for masonry buildings

Katrin Beyer, Radhakrishna Achanta, Bryan German Pantoja Rosero

To predict the response of masonry buildings to various types of loads, engineers use finite element models, specifically solid-element and macro-element models. For predicting masonry responses to seismic events in particular, equivalent frame models-a su ...

SPRINGER2023

ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns

Pascal Fua, Benoît Alain René Guillard, Ren Li

Many approaches to draping individual garments on human body models are realistic, fast, and yield outputs that are differentiable with respect to the body shape on which they are draped. However, they are either unable to handle multi-layered clothing, wh ...

2023

Megapixel SPAD cameras for time-resolved applications

Kazuhiro Morimoto

Progress in optics technology has enriched our daily lives in many ways. Various types of single-photon detector technologies have emerged in the last century. Among these, single-photon avalanche diode (SPAD) technology outperforms other detectors for its ...

EPFL2020

Media Coverage of 3D Visual Tools Used in Urban Participatory Planning

Jens Ingensand, Thibaud Nicolas Chassin

The opportunities provided by adopting digitally-generated visual tools in urban participatory planning are compelling. These visual tools can promote interactions between authorities and citizens and among citizens. However, the urban participatory practi ...

IGI GLOBAL2023

Automated post-earthquake damage assessment of stone masonry buildings integrating machine learning, computer vision, and physics-based modeling

Bryan German Pantoja Rosero

Current post-earthquake damage assessment methodologies are not only time-consuming but also subjective in nature and difficult to document. Recent advancements in artificial intelligence and technological devices make it possible to accomplish this task a ...

EPFL2023

Voxel2Mesh: 3D Mesh Model Generation from Volumetric Data

Pascal Fua, Graham Knott, Edoardo Remelli, Pamuditha Udaranga Wickramasinghe

CNN-based volumetric methods that label individual voxels now dominate the field of biomedical segmentation. However, 3D surface representations are often required for proper analysis. They can be obtained by post-processing the labeled volumes which typic ...

2020

Robust Isometric Non-Rigid Structure-From-Motion

Shaifali Parashar

Non-Rigid Structure-from-Motion (NRSfM) reconstructs a deformable 3D object from keypoint correspondences established between monocular 2D images. Current NRSfM methods lack statistical robustness, which is the ability to cope with correspondence errors. T ...

IEEE COMPUTER SOC2022

Functional Inverse Problems on Spheres: Theory, Algorithms and Applications

Matthieu Martin Jean-André Simeoni

Many scientific inquiries in natural sciences involve approximating a spherical field -namely a scalar quantity defined over a continuum of directions- from generalised samples of the latter (e.g. directional samples, local averages, etc). Such an approxim ...

EPFL2020

Synthesis and Analysis of 3D shapes with Geometric Deep Learning in Computer-Aided Engineering

Edoardo Remelli

In this thesis, we advocate that Computer-Aided Engineering could benefit from a Geometric Deep Learning revolution, similarly to the way that Deep Learning revolutionized Computer Vision. To do so, we consider a variety of Computer-Aided Engineering pr ...

EPFL2022

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

Pascal Fua, Mathieu Salzmann, Victor Constantin, Erhan Gündogdu

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 ...

IEEE2019

Fast 3D Modeling of Prosthetic Robotic Hands Based on a Multi-Layer Deformable Design

Daniel Thalmann

Current research of designing prosthetic robotic hands mainly focuses on improving their functionality by devising new mechanical structures and actuation systems. Most of existing work relies on a single structure/system (e.g., bone-only or tissue-only) a ...

WHIOCE PUBLISHING PTE LTD, SINGAPORE2022

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

Pascal Fua, Katrin Beyer, Radhakrishna Achanta, Fernando Perez Cruz, Bryan German Pantoja Rosero, Mateusz Kozinski

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 ...

2022