Explanipedia

Towards Fast Option Pricing PDE Solvers Powered by PIELM Open

Ashwanth Srinivasan, Amir Said, Sathwik Pentela, Vikas Dwivedi, B. Srinivasan · 2025

Partial differential equation (PDE) solvers underpin modern quantitative finance, governing option pricing and risk evaluation. Physics-Informed Neural Networks (PINNs) have emerged as a promising approach for solving the forward and inver…

Heritage Value Mapping: An Automated Tool for Visual Assessment and Conservation Enhancement Open

Joseph S. Sherif, Amir Said, Riham Adel, G. Nagy · 2025

Heritage buildings hold historical, cultural, and traditional significance, making their preservation crucial for future generations. However, when the intrinsic values of these buildings are not fully recognized, it can lead to the loss o…

AI-Powered Smart Stick Enhancing Mobility and Safety for the Visually Impaired Open

Aya Abdelaty, Amir Said · 2025

Evaluating Machine Learning Techniques for Breast Cancer Detection: A Comprehensive Review Open

Owen Kresse, Y. Rezk, Amir Said, Rimal Mousa, Matheus Sampaio Ibrahim , et al. · 2025

Pelatihan Pengelolaan Data Menggunakan Aplikasi Microsoft Excel Bagi Guru Di Sd 187 Kabupaten Barru Open

Fajrin Baids, Nur Ibrahim, Nurul Mutahara B, Amir Said, Herawan Hisanan · 2024

Efficient management of academic and administrative data remains a challenge for many teachers in Indonesia, including those at UPTD SD 187 Barru. This training program was designed to enhance teachers' skills in utilizing Microsoft Excel,…

GestureLink: Immersive Hand Guided Virtual Interface Open

Amir Said, Sherif Said, Anand Khatri, Sachin Bhosale · 2024

This report introduces an innovative Hand Gesture Mouse Controlling system that utilizes hand gestures captured via a webcam through a colour detection technique. This system enables users to navigate the computer cursor and perform clicki…

Sort-free Gaussian Splatting via Weighted Sum Rendering Open

Qiqi Hou, Randall Rauwendaal, Zifeng Li, Hoang Le, Farzad Farhadzadeh , et al. · 2024

Recently, 3D Gaussian Splatting (3DGS) has emerged as a significant advancement in 3D scene reconstruction, attracting considerable attention due to its ability to recover high-fidelity details while maintaining low complexity. Despite the…

Neural Graphics Texture Compression Supporting Random Access Open

Farzad Farhadzadeh, Qiqi Hou, Hoang Le, Amir Said, Randall Rauwendaal , et al. · 2024

Advances in rendering have led to tremendous growth in texture assets, including resolution, complexity, and novel textures components, but this growth in data volume has not been matched by advances in its compression. Meanwhile Neural Im…

Low-Latency Neural Stereo Streaming Open

Qiqi Hou, Farzad Farhadzadeh, Amir Said, Guillaume Sautière, Hoang D. Le · 2024

The rise of new video modalities like virtual reality or autonomous driving has increased the demand for efficient multi-view video compression methods, both in terms of rate-distortion (R-D) performance and in terms of delay and runtime. …

New Filters for Image Interpolation and Resizing Open

Amir Said · 2023

We propose a new class of kernels to simplify the design of filters for image interpolation and resizing. Their properties are defined according to two parameters, specifying the width of the transition band and the height of a unique side…

Bitstream Organization for Parallel Entropy Coding on Neural Network-based Video Codecs Open

Amir Said, Hoang Le, Farzad Farhadzadeh · 2023

Video compression systems must support increasing bandwidth and data throughput at low cost and power, and can be limited by entropy coding bottlenecks. Efficiency can be greatly improved by parallelizing coding, which can be done at much …

MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device Open

Ties van Rozendaal, Tushar Singhal, Hoang Le, Guillaume Sautière, Amir Said , et al. · 2023

Neural video codecs have recently become competitive with standard codecs such as HEVC in the low-delay setting. However, most neural codecs are large floating-point networks that use pixel-dense warping operations for temporal modeling, m…

Introduction to Arithmetic Coding -- Theory and Practice Open

Amir Said · 2023

This introduction to arithmetic coding is divided in two parts. The first explains how and why arithmetic coding works. We start presenting it in very general terms, so that its simplicity is not lost under layers of implementation details…

Differentiable bit-rate estimation for neural-based video codec enhancement Open

Amir Said, Manish Kumar, Reza Pourreza · 2022

Neural networks (NN) can improve standard video compression by pre- and\npost-processing the encoded video. For optimal NN training, the standard codec\nneeds to be replaced with a codec proxy that can provide derivatives of\nestimated bit…

Optimized Learned Entropy Coding Parameters for Practical Neural-Based Image and Video Compression Open

Amir Said, Reza Pourreza, Hoang Le · 2022

Neural-based image and video codecs are significantly more power-efficient\nwhen weights and activations are quantized to low-precision integers. While\nthere are general-purpose techniques for reducing quantization effects, large\nlosses …

Boosting neural video codecs by exploiting hierarchical redundancy Open

Reza Pourreza, Hoang Le, Amir Said, Guillaume Sautière, Auke Wiggers · 2022

In video compression, coding efficiency is improved by reusing pixels from previously decoded frames via motion and residual compensation. We define two levels of hierarchical redundancy in video frames: 1) first-order: redundancy in pixel…

MobileCodec: Neural Inter-frame Video Compression on Mobile Devices Open

Hoang Le, Liang Zhang, Amir Said, Guillaume Sautière, Yang Yang , et al. · 2022

Realizing the potential of neural video codecs on mobile devices is a big technological challenge due to the computational complexity of deep networks and the power-constrained mobile hardware. We demonstrate practical feasibility by lever…

MobileCodec Open

Hoang Le, Liang Zhang, Amir Said, Guillaume Sautière, Yang Yang , et al. · 2022

Realizing the potential of neural codecs on real-world mobile devices is a big technological challenge due to the inherent conflict between the computational complexity of deep networks and the power-constrained mobile hardware performance…

Transform Network Architectures for Deep Learning Based End-to-End Image/Video Coding in Subsampled Color Spaces Open

Hilmi E. Egilmez, Ankitesh Kumar Singh, Muhammed Coban, Marta Karczewicz, Yinhao Zhu , et al. · 2021

Most of the existing deep learning based end-to-end image/video coding (DLEC) architectures are designed for non-subsampled RGB color format. However, in order to achieve a superior coding performance, many state-of-the-art block-based com…

Parametric Graph-Based Separable Transforms For Video Coding Open

Hilmi E. Egilmez, Oğuzhan Teke, Amir Said, Vadim Seregin, Marta Karczewicz · 2020

In many video coding systems, separable transforms (such as two-dimensional DCT-2) have been used to code block residual signals obtained after prediction. This paper proposes a parametric approach to build graph-based separable transforms…

Parallelized Rate-Distortion Optimized Quantization Using Deep Learning Open

Dana Kianfar, Auke Wiggers, Amir Said, Reza Pourreza, Taco Cohen · 2020

Rate-Distortion Optimized Quantization (RDOQ) has played an important role in the coding performance of recent video compression standards such as H.264/AVC, H.265/HEVC, VP9 and AV1. This scheme yields significant reductions in bit-rate at…

Low-Complexity Transform Adjustments for Video Coding Open

Amir Said, Hilmi E. Egilmez, Yung‐Hsuan Chao · 2019

Recent video codecs with multiple separable transforms can achieve significant coding gains using asymmetric trigonometric transforms (DCTs and DSTs), because they can exploit diverse statistics of residual block signals. However, they add…

Machine learning for media compression: challenges and opportunities Open

Amir Said · 2018

Machine learning for media compression: challenges and opportunities amir saidMachine learning (ML) has been producing major advances in several technological fields and can have a significant impact on media coding.However, fast progress …

Position dependent prediction combination for intra-frame video coding Open

Amir Said, Xin Zhao, Marta Karczewicz, Jianle Chen, Feng Zou · 2016

Intra-frame prediction in the High Efficiency Video Coding (HEVC) standard can be empirically improved by applying sets of recursive two-dimensional filters to the predicted values. However, this approach does not allow (or complicates sig…

Highly efficient non-separable transforms for next generation video coding Open

Amir Said, Xin Zhao, Marta Karczewicz, Hilmi E. Egilmez, Vadim Seregin , et al. · 2016

For the last few decades, the application of signal-adaptive transform coding to video compression has been stymied by the large computational complexity of matrix-based solutions. In this paper, we propose a novel parametric approach to g…

Amir Said YOU? Author Swipe