Lists (1)
Stars
Modern observability platform: 10x easier, 140x lower storage cost, petabyte scale. Open-source alternative to Elasticsearch/Splunk/Datadog for logs, metrics, traces, RUM, and more.
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
ABME AdaFNIO AMT BiM-VFI BiT CBBD CDFI CtxSyn DBVI DC-BVFI DQBC DRVI DvP EAFI EBME EDC EDEN EDENVFI EDSC EMA-VFI FGDCN FILM FLAVR GIMM-VFI HFD HiFI H-VFI IFRNet InterpAny-Clearer IQ-VFI JNMR LADDER…
The MAGSAC algorithm for robust model fitting without using an inlier-outlier threshold
Minimal solvers for calibrated camera pose estimation
Source code for the ECCV 2022 paper "Benchmarking Localization and Mapping for Augmented Reality".
The Open Source Alternative to Cluely - A lightning-fast, privacy-first AI assistant that works seamlessly during meetings, interviews, and conversations without anyone knowing. Built with Tauri fo…
Back to the Feature: Learning Robust Camera Localization from Pixels to Pose (CVPR 2021)
Tools to Design or Visualize Architecture of Neural Network
Ready-to-use TensorRT image classification pipeline that automatically adapts to any CNN model. GPU-aware design allows running multiple instances across different GPUs safely.
High-performance C++ YOLO inference engine with dual CUDA streams achieving 125+ FPS on RTX 3090 for yoloV11 large model @ 1280x1280 resolution. Supports YOLOv8/YOLOv11 models with automatic adapta…
A fast multi-producer, multi-consumer lock-free concurrent queue for C++11
Unreal Engine 5 Guide. Learn to develop games for Windows, Linux, macOS, iOS, Android, Xbox Series X|S, PlayStation 5, Nintendo Switch.
Complete solutions to the Programming Massively Parallel Processors Edition 4
A minimal smart resume maker we all need !
[ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.
SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022
Systems design is the process of defining the architecture, modules, interfaces, and data for a system to satisfy specified requirements. Systems design could be seen as the application of systems …
This repository includes all the interview preparation questions for Amazon SDE role
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
PixTrack is a Computer Vision method for Object Tracking which uses NeRF templates and feature-metric alignment to robustly track the 6DoF pose of a known object.
PlaneRCNN detects and reconstructs piece-wise planar surfaces from a single RGB image