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

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.

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 ...

Chemical gas dispersion can represent a severe threat to human and animal lives, as well as to the environment. Constructing a map of the distribution of gas in a fast and reliable manner is critical to ensure accurate monitoring of at-risk facilities and ...

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 ...

In this thesis, we study the 3 challenges described above. First, we study different reconstruction techniques and assess the fidelity of each reconstruction results by means of structured illumination and phase conjugation. By reconstructing the 3D refrac ...

We present a pipeline for the automatic generation of digital twins of free-standing buildings for damage assessment. Our method takes multiple view images of the target building as input and processes them to produce a 3D model in levels of detail (LOD) f ...

In the past decade, optical diffraction tomography has gained a lot of attention for its ability to create label-free three-dimensional (3D) images of the refractive index distribution of biological samples using scattered fields measured through holograph ...

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 ...

We propose a new modelling approach for daily activity scheduling which integrates the different daily scheduling choice dimensions (activity participation, location, schedule, duration and transportation mode) into a single optimisation problem. The funda ...

We present a method for estimating the main properties of human skin, leveraging a hyperspectral dataset of skin tones synthetically generated through a biophysical layered skin model and Monte Carlo light transport simulations. Our approach learns the map ...

While over fields of characteristic at least 5, a normal, projective and Gorenstein del Pezzo surface is geometrically normal, this does not hold for characteristic 2 and 3. There is no characterization of all such non-geometrically normal surfaces, but th ...

Reconstructing 3D shape from 2D sketches has long been an open problem because the sketches only provide very sparse and ambiguous information. In this paper, we use an encoder/decoder architecture for the sketch to mesh translation. When integrated into a ...

Depth sensing is an increasingly important feature in many applications of consumer, automotive, augmented/virtual reality (AR-VR), space and bio-medical imaging. Long range, high depth resolution, high spatial resolution, and high frame rates are often co ...

The wave functions of a disordered two-dimensional electron gas at the quantum-critical Anderson transition are predicted to exhibit multifractal scaling in their real space amplitude. We experimentally investigate the appearance of these characteristics i ...

Tim-domain near-infrared optical tomography (TD NIROT) techniques based on diffuse light were gaining performance over the last years. They are capable of imaging tissue at several centimeters depth and reveal clinically relevant information, such as tissu ...

The human face plays an essential role in social interactions as it brings information about someone's identity, state of mind, or mood. People are, by nature, very good at catching this non-spoken information. Therefore, scientists have been interested in ...

Urban air quality is a major concern in the context of human health since cities are at the same time emission hot spots and home to a large fraction of the world's population. Airborne imaging spectrometers may be a valuable addition to traditional air po ...

Representing and reconstructing 3D deformable shapes are two tightly linked problems that have long been studied within the computer vision field. Deformable shapes are truly ubiquitous in the real world, whether be it specific object classes such as human ...

Our aim is to develop a 3D model unit of cardiac muscle: an in-vitro analog of the trabeculae carneae found in vivo. As a base hydrogel matrix for cardiomyocyte culture in 3D, we develop a blend of decellularized extracellular matrix (dECM) and fibrin. Thi ...

We consider the influence of transverse confinement on the instability properties of velocity and density distributions reminiscent of those pertaining to exchange flows in stratified inclined ducts, such as the recent experiment of Lefauve et al. [J. Flui ...

We present an image-based pipeline for generating geometrical digital twins (GDTs) of stone masonry elements with detail down to the stone level. For this purpose, we acquire RGB images of the individual stones and of the wall during the construction phase ...

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

Chat with Graph Search

Deep Learning for 3D Surface Modelling and Reconstruction

Clustering and Informative Path Planning for 3D Gas Distribution Mapping: Algorithms and Performance Evaluation

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

Advanced Techniques in Optical Diffraction Tomography

Digital twins for post-earthquake damage assessment of free-standing buildings including damage information

Exploring Novel Modalities for Optical Diffraction Tomography

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

Capturing trade-offs between daily scheduling choices

A Hyperspectral Space of Skin Tones for Inverse Rendering of Biophysical Skin Properties

Examples of normal, not geometrically normal, projective Gorenstein del Pezzo surfaces with at most Du Val singularities

Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches

Direct time-of-flight SPAD image sensors for light detection and ranging

Visualizing the multifractal wave functions of a disordered two-dimensional electron gas

2.5 Hz sample rate time-domain near-infrared optical tomography based on SPAD-camera image tissue hemodynamics

Model-based 3D Face Reconstruction

Importance of 3D radiative transfer effects on high-resolution NO2 remote sensing in cities

Learning to Represent and Reconstruct 3D Deformable Objects

Towards an in vitro cardiac model: 3D environment, co-culture, alignment, and mechanical stimulation impact on cell behavior

Effects of spanwise confinement on stratified shear instabilities

Image-based geometric digital twinning for stone masonry elements