Research & Education

ChangeMamba is an open-source tool designed for remote sensing change detection, leveraging a spatio-temporal state space model. It provides robust capabilities for various change detection tasks, including binary change detection (MambaBCD), semantic change detection (MambaSCD), and building damage assessment (MambaBDA). The tool is particularly useful for researchers and scientists working with Earth observation data, facilitating the analysis of changes in land cover and environmental conditions. It offers pre-trained weights for different model sizes (Tiny, Small, Base) and supports training and inference on several benchmark datasets like SYSU, LEVIR-CD+, WHU-CD, SECOND, and xBD. The project is actively maintained with regular updates and has been recognized in IEEE TGRS.

ssm is a powerful tool designed for Bayesian learning and inference within state space models. It offers comprehensive functionalities for simulating, learning, and performing inference across a variety of state space models. The project is currently undergoing a JAX refactor, which aims to leverage JIT compilation and provide enhanced support for GPU and TPU hardware, significantly boosting performance and computational efficiency for complex scientific computing tasks. This makes ssm particularly valuable for researchers and data scientists working with dynamic systems and requiring robust statistical modeling capabilities.

AlphaPose is a robust, open-source system designed for real-time and accurate full-body multi-person pose estimation and tracking. It stands out as one of the first open-source systems to achieve high mAP scores on COCO and MPII datasets. The tool also incorporates an efficient online pose tracker called Pose Flow, which excels in matching poses across frames. Key features include support for COCO 17 keypoints, Halpe 26 and 136 keypoints with tracking, and SMPL integration for 3D pose and shape estimation. AlphaPose is compatible with both Linux and Windows, and a Jittor version is available, offering significant speed improvements during the training stage. It is ideal for researchers and developers working on computer vision projects requiring precise human pose analysis.

Mockmate is an artificial intelligence tool designed to streamline the job interview process for both candidates and companies. For job seekers, it acts as an interview simulator, offering immediate feedback to help them practice and improve their interviewing skills. Companies can leverage Mockmate to automate initial interview stages and efficiently shortlist candidates. It utilizes natural language processing (NLP) to analyze responses, making the candidate selection process more objective and scalable.

AttentionDistillation is a Hugging Face Space application designed for image style transfer. This tool allows users to take the artistic style from a source image and apply it to a target image, creating a new image that adopts the desired aesthetic. It serves as a practical demonstration of attention distillation techniques in AI models, making it valuable for both educational purposes and experimental use. The application is straightforward, requiring users to simply upload two images to achieve the style transfer effect.

Apex Vision AI is a comprehensive AI homework helper and study tool designed to assist college students. It offers instant answers to questions, generates study guides, creates flashcards, and provides practice tests to help students ace their exams. The tool integrates smoothly with major learning management systems like Canvas, Blackboard, and Moodle, and also features an AI Graph & Image solver. Available as a Chrome extension, Apex Vision AI aims to streamline the learning process by offering on-page workflow support without requiring school login data, ensuring privacy while enhancing academic performance.

The AI Chemistry Assistant, part of the FullStackPathway suite, is designed to provide instant and accurate solutions for complex chemical problems. This tool is ideal for students, educators, and professionals seeking to simplify their chemistry-related tasks. It offers a comprehensive approach to problem-solving, leveraging advanced AI to deliver step-by-step solutions and clear explanations. As part of an all-in-one AI toolkit, it integrates seamlessly with other AI tools for various academic and professional needs, making it an indispensable companion for success in chemistry and related fields.

LinFusion SD V1.5 is an AI-powered tool designed for generating images directly from text descriptions. Users can input textual prompts, and the AI will interpret these prompts to produce corresponding visual outputs. Hosted on Hugging Face Spaces, this tool provides a free and accessible platform for individuals looking to create unique images without specialized graphic design skills. It focuses on straightforward image generation based on user-provided text.

drl-zh, or "Deep Reinforcement Learning: Zero to Hero!", offers a comprehensive and hands-on course designed to teach deep reinforcement learning. The curriculum is divided into two main parts: foundational concepts, where users build algorithms like DQN, SAC, and PPO from scratch, and advanced topics, which delve into areas such as curiosity-driven exploration, AlphaZero, and Reinforcement Learning with Human Feedback (RLHF). The course emphasizes learning by doing, with practical exercises ranging from playing Atari games and training robots to fine-tuning Language Models and implementing self-play with MCTS. It's structured around interactive Jupyter notebooks, providing guided TODO sections and complete solutions for reference. The entire experience is optimized for a VS Code environment, with a Dockerized setup for quick and reproducible development.

Hands-On-GPU-Accelerated-Computer-Vision-with-OpenCV-and-CUDA is a comprehensive code repository accompanying a Packt-published book. It focuses on integrating OpenCV with CUDA to leverage NVIDIA GPUs for accelerating computer vision tasks. The repository includes code examples for various chapters, covering topics such as accessing GPU device properties, accelerating searching and sorting algorithms, detecting shapes, object tracking and detection, and processing videos. It's designed for developers working with OpenCV who need to handle complex image data efficiently and in real-time, providing practical techniques for GPU acceleration.

Stammer AI provides a white-label AI SaaS platform designed for users to build and sell their own custom AI agents. The platform facilitates the creation of personalized AI assistants without requiring any coding knowledge. Users can integrate their proprietary knowledge bases to develop more intelligent and context-aware AI agents. Stammer AI offers a comprehensive suite of tools for constructing these agents entirely within its Prompt PP environment, streamlining the development process for various applications.

ICML2023 Papers is a Hugging Face Space designed to provide access to research papers presented at the ICML2023 conference. While the tool's primary function is to serve as a repository for academic research, it is currently paused. Users interested in utilizing this resource are directed to the community tab to request its restart from the author(s). This tool would typically be valuable for academic research, literature reviews, and information retrieval within the field of AI, catering to researchers and students.

rust_sqlite, also known as SQLRite, is a simple embedded database modeled after SQLite but developed entirely in Rust. The project's primary goal is to offer a hands-on approach to understanding database internals by building one from the ground up. It features a cross-platform Tauri 2.0 + Svelte 5 desktop GUI alongside a REPL for interaction. The tool supports core SQL statements like CREATE TABLE, INSERT, SELECT, UPDATE, and DELETE, along with basic transactions. It emphasizes on-disk persistence, a cell-based B-Tree structure, and secondary indexes. The project is actively developed in phases, with current work focusing on durability and concurrency through a Write-Ahead Log (WAL) and multi-reader/single-writer access.

swift-embedded-examples is a collection of demonstration projects designed to help developers learn and implement Embedded Swift. This compilation and language mode allows for the development of baremetal, embedded, and standalone software using the Swift programming language. The repository serves as a valuable resource for understanding how to leverage Swift in embedded systems, offering practical examples that illustrate various functionalities and use cases. It aims to simplify the process of getting started with Embedded Swift development by providing ready-to-use code and project structures, making it easier for developers to explore and build their own embedded applications.

simple-HRNet is an unofficial yet fully compatible implementation of the Deep High-Resolution Representation Learning for Human Pose Estimation paper, built with PyTorch. This tool simplifies the process of human pose estimation, offering compatibility with official pre-trained weights and delivering results consistent with the original implementation. It supports both Windows and Linux environments and includes features like multi-GPU inference, options for retrieving YOLO bounding boxes and HRNet heatmaps, and multi-person support with YOLOv3, YOLOv3-tiny, or YOLOv5. The repository also provides a live demo, scripts for training and testing on datasets like COCO, and support for TensorRT, making it a versatile solution for developers and researchers in computer vision.

f2-nerf is an open-source project designed for fast neural radiance field (NeRF) training, specifically optimized for scenarios involving free camera trajectories. Built primarily on LibTorch, this tool provides a robust framework for efficient 3D scene reconstruction and novel view synthesis. Users can train F2-NeRF on custom data, including images processed with COLMAP or hloc, and generate camera poses. It also includes scripts for rendering test images and creating render paths by interpolating input camera poses. The project leverages several powerful libraries such as tiny-cuda-nn for fast MLP training, happly for PLY I/O, and eigen for linear algebra, making it a comprehensive solution for advanced NeRF applications.

OdaMobil is a mobile application development firm based in Turkey, specializing in custom Android and iOS application development. They focus on delivering superior user experiences through thoughtful design and performance, ensuring applications stand out on Google Play Store and App Store. Their services encompass a wide range of solutions, including augmented reality applications for historical sites like Hagia Sophia, educational apps for universities such as Boğaziçi University, and interactive platforms for popular destinations like Ormanya. OdaMobil also develops specialized software for various industries, including smart transportation, e-commerce, and municipal services, aiming to reduce costs and increase competitiveness for their clients. They also offer solutions like OMapping for illustrated maps, OdaApp for centralized communication, Oniversity for university-specific apps, and OSeller for automating production and sales processes.

SC-GS provides code for Sparse-Controlled Gaussian Splatting, designed for editable dynamic scenes. This open-source tool allows users to effortlessly edit and customize their digital assets through interactive features. It represents motion using sparse control points, which drive 3D Gaussians for high-fidelity rendering. The approach supports both dynamic view synthesis and motion editing, making it versatile for various applications. Recent updates include support for editing static Gaussians from .ply files, improved handling of real-world static objects, and video rendering with interpolation of editing results. It offers two ARAP deformation strategies for motion editing: iterative deformation and deformation from Laplacian initialization, giving users flexibility in achieving desired effects.

InfoShelves Workday Certification app is an AI-driven platform designed to help professionals prepare for Workday certifications. It offers authentic certification practice tests and study notes across various Workday areas, including HCM Pro, Financials, Reporting, and Integration. The platform aims to provide a focused and efficient way to study and pass Workday certification exams, boosting career prospects. With AI-driven discovery, users can master Workday concepts and prepare effectively for their professional development. The app focuses on providing comprehensive exam simulators to ensure users are well-prepared for their certification journey.

SplaTAM is a cutting-edge system designed for Splatting, Tracking, and Mapping 3D Gaussians, enabling dense RGB-D SLAM. This tool, presented at CVPR 2024, is particularly useful for robotics and computer vision applications requiring real-time environmental understanding. Users can capture their own environments using an iPhone or LiDAR-equipped Apple device with the NeRFCapture app, and then process the data either online or offline. SplaTAM supports interactive rendering of reconstructions and allows for the export of splats to .ply files for visualization in external viewers like SuperSplat and PolyCam. It also facilitates 3D Gaussian Splatting on reconstructions and datasets with ground truth poses, making it a versatile tool for researchers and developers in the field.

sdfstudio is a unified, open-source framework designed for neural implicit surface reconstruction, leveraging the foundation of the Nerfstudio project. It provides a modular architecture that allows for the implementation and exploration of different surface reconstruction methods, such as UniSurf, VolSDF, and NeuS. The framework supports various scene representations and datasets, making it a versatile tool for advanced 3D modeling, research, and development in the field of neural implicit surfaces. Its open-source nature encourages community contributions and provides a flexible platform for experimenting with cutting-edge 3D reconstruction techniques.

USRNet is a deep unfolding network for image super-resolution, implementing a model described in a CVPR 2020 paper. This PyTorch-based tool provides code and models for training and testing image super-resolution algorithms. It leverages both learning-based and model-based methods, offering the flexibility of model-based approaches to super-resolve blurry and noisy images across different scale factors, blur kernels, and noise levels using a single unified model. Key features include a data module for clearer HR estimation, a prior module for cleaner HR estimation, and a hyper-parameter module to control outputs. It supports various degradation models, including bicubic degradation and deblurring, and demonstrates strong generalizability to different kernel sizes.

OpenBR (Open Source Biometrics) is a comprehensive toolkit designed for developers and researchers working in the field of biometrics, particularly face recognition. Hosted on GitHub, it offers an open-source solution for building and experimenting with biometric systems. The platform provides the necessary tools and functionalities to implement various biometric algorithms, making it a valuable resource for academic research, prototyping, and custom application development. Users can clone the repository, check out specific release tags, and build the software following detailed instructions for their operating system. This open-source nature fosters community contributions and allows for transparent development in biometric identification.

vedadet is a single-stage object detection toolbox built on PyTorch, offering a modular design that re-engineers MMDetection for enhanced flexibility and deployment. It decomposes the detector into four key parts: data pipeline, model, postprocessing, and criterion, making it straightforward to convert PyTorch models into TensorRT engines. This design facilitates efficient deployment on NVIDIA devices such as Tesla V100, Jetson Nano, and Jetson AGX Xavier. The toolbox supports several popular single-stage detectors, including RetinaNet and FCOS, right out of the box. Its friendly integration with TensorRT allows for easy model conversion and deployment through both Python and C++ front-ends, making it a powerful tool for developers working on object detection tasks.