All Projects → StarsX → NonuniformBlur

StarsX / NonuniformBlur

Licence: MIT License
Authors' implementation of my SIGGRAPH Asia 2019 Technical Briefs (The Power of Box Filters: Real-time Approximation to Large Convolution Kernel by Box-filtered Image Pyramid) demo I (just for reference). A very fast approximation to large-kernel Gaussian blur with nonuniform blur radii, by making use of box-filtered mip maps V-cycle (theoratica…

Programming Languages

C++
36643 projects - #6 most used programming language
c
50402 projects - #5 most used programming language

Projects that are alternatives of or similar to NonuniformBlur

IrradianceMap
Authors' implementation of my SIGGRAPH Asia 2019 Technical Briefs (The Power of Box Filters: Real-time Approximation to Large Convolution Kernel by Box-filtered Image Pyramid) demo II. Real-time dynamic irradiance mapping.
Stars: ✭ 48 (-42.17%)
Mutual labels:  convolution, siggraph-asia, mipmap, box-filters
deep-scite
🚣 A simple recommendation engine (by way of convolutions and embeddings) written in TensorFlow
Stars: ✭ 20 (-75.9%)
Mutual labels:  convolution
Convolve
Simple demonstration of separable convolutions
Stars: ✭ 198 (+138.55%)
Mutual labels:  convolution
dsp
DSP and filtering library
Stars: ✭ 36 (-56.63%)
Mutual labels:  convolution
Image Js
Image processing and manipulation in JavaScript
Stars: ✭ 241 (+190.36%)
Mutual labels:  convolution
algorithmia
No description or website provided.
Stars: ✭ 15 (-81.93%)
Mutual labels:  convolution
Etl
Blazing-fast Expression Templates Library (ETL) with GPU support, in C++
Stars: ✭ 190 (+128.92%)
Mutual labels:  convolution
riconv
Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
Stars: ✭ 43 (-48.19%)
Mutual labels:  convolution
minirocket
MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification
Stars: ✭ 166 (+100%)
Mutual labels:  convolution
Scaffold-Map
Robust, efficient and low distortion bijective mapping in 2D and 3D
Stars: ✭ 51 (-38.55%)
Mutual labels:  siggraph-asia
susa
High Performance Computing (HPC) and Signal Processing Framework
Stars: ✭ 55 (-33.73%)
Mutual labels:  convolution
Mono3D
Source code for "Mononizing Binocular Videos" (SIGGRAPH Asia 2020)
Stars: ✭ 33 (-60.24%)
Mutual labels:  siggraph-asia
spark-convolution-patch
Convolution and other super-patches (blur, sharpen)
Stars: ✭ 74 (-10.84%)
Mutual labels:  convolution
Skimcaffe
Caffe for Sparse Convolutional Neural Network
Stars: ✭ 230 (+177.11%)
Mutual labels:  convolution
dsp-theory
Theory of digital signal processing (DSP): signals, filtration (IIR, FIR, CIC, MAF), transforms (FFT, DFT, Hilbert, Z-transform) etc.
Stars: ✭ 643 (+674.7%)
Mutual labels:  convolution
Laser
The HPC toolbox: fused matrix multiplication, convolution, data-parallel strided tensor primitives, OpenMP facilities, SIMD, JIT Assembler, CPU detection, state-of-the-art vectorized BLAS for floats and integers
Stars: ✭ 191 (+130.12%)
Mutual labels:  convolution
PyTsetlinMachineCUDA
Massively Parallel and Asynchronous Architecture for Logic-based AI
Stars: ✭ 37 (-55.42%)
Mutual labels:  convolution
shellnet
ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics
Stars: ✭ 80 (-3.61%)
Mutual labels:  convolution
cnn np
使用numpy构建cnn复习深度学习知识
Stars: ✭ 33 (-60.24%)
Mutual labels:  convolution
WebSight
Aiding the visually impaired through real time augmented reality, AI object detection, WebGL shaders effects such as edge detection, and colour adjustments.
Stars: ✭ 26 (-68.67%)
Mutual labels:  convolution

NonuniformBlur

A very fast approximation to large-kernel Gaussian blur with nonuniform blur radii, by making use of box-filtered mip maps (theoratically related to Haar wavelet tranforms). The mathematical model can be found in the PDF file.

Nonuniform blur result

Nonuniform blur result PR

Nonuniform blur result NPR

Nonuniform blur result Me

Hot keys:

[F1] show/hide FPS

[Space] pause/play animation

[P] pipeline type switch

Prerequisite: https://github.com/StarsX/XUSG

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].