- UW Madison
- http://varun19299.github.io/
- @varun19299
Highlights
- Pro
Stars
Detect dominant periodicity in equidistant time series
High-resolution models for human tasks.
Refine high-quality datasets and visual AI models
Pytorch implementation of Simplified Structured State-Spaces for Sequence Modeling (S5)
A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift
Event-based camera data representation and processing. Some common representations and reference codes.
[ECCV 2022] We investigated a broad range of neural network elements and developed a robust perceptual similarity metric. Our shift-tolerant perceptual similarity metric (ST-LPIPS) is consistent wi…
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
A Python package for decoding RAW and DAT files (Prophesee) to structured NumPy arrays of events.
A simple and efficient wrapper for reading videos as NumPy tensors
A Unified Framework for Compressive Video Recovery from Coded Exposure Techniques (WACV 2021)
Mitsuba 3: A Retargetable Forward and Inverse Renderer
FFCV: Fast Forward Computer Vision (and other ML workloads!)
GPU-accelerated bio-image analysis focusing on 3D+t microscopy image data
[CVPR 2021] Multi-Modal-CelebA-HQ: A Large-Scale Text-Driven Face Generation and Understanding Dataset
Event-based Vision Resources. Community effort to collect knowledge on event-based vision technology (papers, workshops, datasets, code, videos, etc)
Matplotlib styles for scientific plotting
Mitsuba 2: A Retargetable Forward and Inverse Renderer
Pytorch implementation of SIREN - Implicit Neural Representations with Periodic Activation Function
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
Main development repository for GAP - Groups, Algorithms, Programming, a System for Computational Discrete Algebra
Python library able to solve typical coding theory textbook exercises.
A performant NumPy extension for Galois fields and their applications
Reproducing RigL (ICML 2020) as a part of ML Reproducibility Challenge 2020
A fast and simple perlin noise generator using numpy