LaunchGemini
Follow
Lists (2)
Starred repositories
The next generation deep reinforcement learning tookit
Bounty Board is a decentralized platform designed to streamline Web3 community activities.
Secure storage system based on cryptography｜基于密码学的安全存储系统
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
Deforum extension for AUTOMATIC1111's Stable Diffusion webui
Text to image synthesis using thought vectors
[CVPR 2018] Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks
CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
Mask Transfiner for High-Quality Instance Segmentation, CVPR 2022
Major Project - Sign Language To Text Conversion Using Python, Computer Vision and Machine Learning
PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
AwesomeBump is a free program written using Qt library designed to generate normal, height, specular or ambient occlusion textures from a single image. Since the image processing is done in 99% on …
Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"
CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks
Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022
[ICLR'25] 3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
Implementation of various self-attention mechanisms focused on computer vision. Ongoing repository.
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
The NASA Vision Workbench is a general purpose image processing and computer vision library developed by the Autonomous Systems and Robotics (ASR) Area in the Intelligent Systems Division at the NA…
This repository contains the source code of our work on designing efficient CNNs for computer vision
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
Build fully-functioning computer vision models with PyTorch
Repository for PyImageSearch Crash Course on Computer Vision and Deep Learning
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
Yet another vine copula package, using PyTorch.
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
Nexa SDK is a comprehensive toolkit for supporting GGML and ONNX models. It supports text generation, image generation, vision-language models (VLM), Audio Language Model, auto-speech-recognition (…
The first open autoregressive foundational video AI model.
3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion
