Publication

Reconfigurable Forward Homography Estimation System for Real-Time Applications

Publications associées (31)

Aggregating Spatial and Photometric Context for Photometric Stereo

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

EPFL2024

Secure Interface Design Leveraging Hardware/Software Support

Atri Bhattacharyya

Computer systems rely heavily on abstraction to manage the exponential growth of complexity across hardware and software. Due to practical considerations of compatibility between components of these complex systems across generations, developers have favou ...

EPFL2024

EdgeAI-Aware Design of In-Memory Computing Architectures

Marco Antonio Rios

Driven by the demand for real-time processing and the need to minimize latency in AI algorithms, edge computing has experienced remarkable progress. Decision-making AI applications stand out for their heavy reliance on data-centric operations, predominantl ...

EPFL2024

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Evann Pierre Guy Courdier

Deep learning has revolutionized the field of computer vision, a success largely attributable to the growing size of models, datasets, and computational power. Simultaneously, a critical pain point arises as several computer vision applications are deploye ...

EPFL2024

The time-domain Cartesian multipole expansion of electromagnetic fields

Farhad Rachidi-Haeri, Marcos Rubinstein, Elias Per Joachim Le Boudec, Nicolas Mora Parra, Chaouki Kasmi, Emanuela Radici

Time-domain solutions of Maxwell’s equations in homogeneous and isotropic media are paramount to studying transient or broadband phenomena. However, analytical solutions are generally unavailable for practical applications, while numerical solutions are co ...

Nature Publishing Group2024

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Seyed Mohammad Mahdi Johari

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 ...

EPFL2024

Live-cell imaging powered by computation

Suliana Manley, Florian Jug

The proliferation of microscopy methods for live-cell imaging offers many new possibilities for users but can also be challenging to navigate. The prevailing challenge in live-cell fluorescence microscopy is capturing intra-cellular dynamics while preservi ...

Nature Portfolio2024

Towards Scalable Electronics: Synthetic 2D Materials for Large-Area 2D Circuit Integration

Zhenyu Wang

In the past decades, a significant increase of the transistor density on a chip has led to exponential growth in computational power driven by Moore's law. To overcome the bottleneck of traditional von-Neumann architecture in computational efficiency, effo ...

EPFL2024

Accelerator-driven Data Arrangement to Minimize Transformers Run-time on Multi-core Architectures

David Atienza Alonso, Giovanni Ansaloni, Alireza Amirshahi

The increasing complexity of transformer models in artificial intelligence expands their computational costs, memory usage, and energy consumption. Hardware acceleration tackles the ensuing challenges by designing processors and accelerators tailored for t ...

2024

Reconfigurable Forward Homography Estimation System for Real-Time Applications

Aggregating Spatial and Photometric Context for Photometric Stereo

Secure Interface Design Leveraging Hardware/Software Support

EdgeAI-Aware Design of In-Memory Computing Architectures

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

The time-domain Cartesian multipole expansion of electromagnetic fields

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Live-cell imaging powered by computation

Towards Scalable Electronics: Synthetic 2D Materials for Large-Area 2D Circuit Integration

Accelerator-driven Data Arrangement to Minimize Transformers Run-time on Multi-core Architectures

Graph Chatbot

Aggregating Spatial and Photometric Context for Photometric Stereo

Secure Interface Design Leveraging Hardware/Software Support

EdgeAI-Aware Design of In-Memory Computing Architectures

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

The time-domain Cartesian multipole expansion of electromagnetic fields

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Live-cell imaging powered by computation

Towards Scalable Electronics: Synthetic 2D Materials for Large-Area 2D Circuit Integration

Accelerator-driven Data Arrangement to Minimize Transformers Run-time on Multi-core Architectures

Applications of the thawed Gaussian approximation to electronic spectroscopy

Applications of the thawed Gaussian approximation to electronic spectroscopy