Concept
Carmack's Reverse
Publications associées (24)
Advancing Self-Supervised Deep Learning for 3D Scene Understanding
Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...
EPFL2024Synchrotron-based phase-contrast micro-CT as a tool for understanding pulmonary vascular pathobiology and the 3-D microanatomy of alveolar capillary dysplasia
This study aimed to explore the value of synchrotron-based phase-contrast microcomputed tomography (micro-CT) in pulmonary vascular pathobiology. The microanatomy of the lung is complex with intricate branching patterns. Tissue sections are therefore diffi ...
AMER PHYSIOLOGICAL SOC2020SynDeMo: Synergistic Deep Feature Alignment for Joint Learning of Depth and Ego-Motion
Jean-Philippe Thiran, Mohammad Saeed Rad
Despite well-established baselines, learning of scene depth and ego-motion from monocular video remains an ongoing challenge, specifically when handling scaling ambiguity issues and depth inconsistencies in image sequences. Much prior work uses either a su ...
IEEE COMPUTER SOC2019An Adaptive Parameterization for Efficient Material Acquisition and Rendering
One of the key ingredients of any physically based rendering system is a detailed specification characterizing the interaction of light and matter of all materials present in a scene, typically via the Bidirectional Reflectance Distribution Function (BRDF) ...
ASSOC COMPUTING MACHINERY2018An Adaptive Parameterization for Efficient Material Acquisition and Rendering
One of the key ingredients of any physically based rendering system is a detailed specification characterizing the interaction of light and matter of all materials present in a scene, typically via the Bidirectional Reflectance Distribution Function (BRDF) ...
ASSOC COMPUTING MACHINERY2018Fast Segmentation from Blurred Data in 3D Fluorescence Microscopy
Michaël Unser, Martin Kurt Storath
We develop a fast algorithm for segmenting 3D images from linear measurements based on the Potts model (or piecewise constant Mumford-Shah model). To that end, we first derive suitable space discretizations of the 3D Potts model, which are capable of deali ...
2017